{"id":"https://openalex.org/W1484478478","doi":"https://doi.org/10.1109/cdc.2003.1273053","title":"Policy gradient stochastic approximation algorithms for adaptive control of constrained time varying markov decision processes","display_name":"Policy gradient stochastic approximation algorithms for adaptive control of constrained time varying markov decision processes","publication_year":2004,"publication_date":"2004-07-08","ids":{"openalex":"https://openalex.org/W1484478478","doi":"https://doi.org/10.1109/cdc.2003.1273053","mag":"1484478478"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2003.1273053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2003.1273053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"42nd IEEE International Conference on Decision and Control (IEEE Cat. No.03CH37475)","raw_type":"proceedings-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/A5064028141","display_name":"Felisa J. V\u00e1zquez Abad","orcid":null},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]},{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"F.J. Vazquez Abad","raw_affiliation_strings":["D\u00e9partement d'informatique et recherche op\u00e9rationnelle, Universit\u00e9 de Montreal, QUE, Canada","Departement d'Informatique et Recherche Oper., Montreal Univ., Que., Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"D\u00e9partement d'informatique et recherche op\u00e9rationnelle, Universit\u00e9 de Montreal, QUE, Canada","institution_ids":["https://openalex.org/I4210111842","https://openalex.org/I70931966"]},{"raw_affiliation_string":"Departement d'Informatique et Recherche Oper., Montreal Univ., Que., Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068804090","display_name":"Vikram Krishnamurthy","orcid":"https://orcid.org/0000-0002-4170-6056"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"V. Krishnamurthy","raw_affiliation_strings":["Department of Electrical Engineering, University of British Columbia, Vancouver, Canada","University of British Columbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of British Columbia, Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"University of British Columbia","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2383,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.91833719,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"3","issue":null,"first_page":"2823","last_page":"2828"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9972000122070312,"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":0.9972000122070312,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9968000054359436,"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/T10320","display_name":"Neural Networks and Applications","score":0.9846000075340271,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6909670829772949},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6218990683555603},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.50160813331604},{"id":"https://openalex.org/keywords/adaptive-control","display_name":"Adaptive control","score":0.4970298111438751},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4850177466869354},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4666794538497925},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4642098546028137},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.45445868372917175},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.4393719434738159},{"id":"https://openalex.org/keywords/stochastic-control","display_name":"Stochastic control","score":0.4322276711463928},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.26743263006210327},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22748708724975586},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.2264271378517151},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16574418544769287},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0756598711013794}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6909670829772949},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6218990683555603},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.50160813331604},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.4970298111438751},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4850177466869354},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4666794538497925},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4642098546028137},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.45445868372917175},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.4393719434738159},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.4322276711463928},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26743263006210327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22748708724975586},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.2264271378517151},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16574418544769287},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0756598711013794},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2003.1273053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2003.1273053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"42nd IEEE International Conference on Decision and Control (IEEE Cat. No.03CH37475)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W184225095","https://openalex.org/W1504265534","https://openalex.org/W1557287189","https://openalex.org/W1576452626","https://openalex.org/W2119792915","https://openalex.org/W2161142726","https://openalex.org/W2235056388","https://openalex.org/W2266946488","https://openalex.org/W2798766386","https://openalex.org/W4205326910","https://openalex.org/W4253284464","https://openalex.org/W4254090244"],"related_works":["https://openalex.org/W3198596521","https://openalex.org/W1982461629","https://openalex.org/W2023682788","https://openalex.org/W2162655762","https://openalex.org/W2031153922","https://openalex.org/W2692631447","https://openalex.org/W259765859","https://openalex.org/W2729904366","https://openalex.org/W2122715318","https://openalex.org/W1836203719"],"abstract_inverted_index":{"We":[0,78],"present":[1,79],"constrained":[2,14],"stochastic":[3,23],"approximation":[4,24],"algorithms":[5,25,59,83,106],"for":[6],"computing":[7],"the":[8,29,32,38,42,71,105],"locally":[9],"optimal":[10],"policy":[11],"of":[12,28,31,70,82],"a":[13],"average":[15],"cost":[16,33],"finite":[17],"state":[18],"Markov":[19],"decision":[20],"process.":[21],"The":[22,58],"require":[26,67],"computation":[27],"gradient":[30,52,94],"function":[34],"with":[35],"respect":[36],"to":[37],"parameter":[39],"that":[40],"characterizes":[41],"randomized":[43],"policy.":[44],"This":[45],"is":[46],"computed":[47],"by":[48],"novel":[49],"simulation":[50,62],"based":[51,63,84],"estimation":[53],"schemes":[54],"involving":[55],"weak":[56],"derivatives.":[57],"proposed":[60,107],"are":[61],"and":[64,93,112],"do":[65],"not":[66],"explicit":[68],"knowledge":[69],"underlying":[72],"parameters":[73],"such":[74,102],"as":[75,103],"transition":[76],"probabilities.":[77],"three":[80],"classes":[81],"on":[85],"primal":[86,96],"dual":[87],"methods,":[88],"augmented":[89],"Lagrangian":[90],"(multiplier)":[91],"methods":[92,101],"projection":[95],"methods.":[97],"Unlike":[98],"neuro-dynamic":[99],"programming":[100],"Q-Learning,":[104],"here":[108],"can":[109],"handle":[110],"constraints":[111],"time":[113],"varying":[114],"parameters.":[115]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}