{"id":"https://openalex.org/W3185475917","doi":"https://doi.org/10.1109/cdc45484.2021.9682829","title":"On the Convergence of Reinforcement Learning in Nonlinear Continuous State Space Problems","display_name":"On the Convergence of Reinforcement Learning in Nonlinear Continuous State Space Problems","publication_year":2021,"publication_date":"2021-12-14","ids":{"openalex":"https://openalex.org/W3185475917","doi":"https://doi.org/10.1109/cdc45484.2021.9682829","mag":"3185475917"},"language":"en","primary_location":{"id":"doi:10.1109/cdc45484.2021.9682829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9682829","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 60th IEEE Conference on Decision and Control (CDC)","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/A5072338368","display_name":"Raman Goyal","orcid":"https://orcid.org/0000-0002-8128-3051"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Raman Goyal","raw_affiliation_strings":["Texas A&M University, College Station, TX, USA"],"affiliations":[{"raw_affiliation_string":"Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061286389","display_name":"Suman Chakravorty","orcid":"https://orcid.org/0000-0003-3074-3406"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suman Chakravorty","raw_affiliation_strings":["Texas A&M University, College Station, TX, USA"],"affiliations":[{"raw_affiliation_string":"Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115595561","display_name":"Ran Wang","orcid":"https://orcid.org/0000-0002-3606-3527"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ran Wang","raw_affiliation_strings":["Texas A&M University, College Station, TX, USA"],"affiliations":[{"raw_affiliation_string":"Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090447176","display_name":"Mohamed Naveed Gul Mohamed","orcid":"https://orcid.org/0000-0001-5718-2261"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohamed Naveed Gul Mohamed","raw_affiliation_strings":["Texas A&M University, College Station, TX, USA"],"affiliations":[{"raw_affiliation_string":"Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072338368"],"corresponding_institution_ids":["https://openalex.org/I91045830"],"apc_list":null,"apc_paid":null,"fwci":0.8727,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6259708,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"9","issue":null,"first_page":"2969","last_page":"2975"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9986000061035156,"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/T11749","display_name":"Iterative Learning Control Systems","score":0.9983999729156494,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7760509252548218},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.706040620803833},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.592717707157135},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5882182121276855},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5829485654830933},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4001751244068146},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.34000587463378906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3007965683937073},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25865721702575684},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.13622862100601196},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08166924118995667},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.07321077585220337},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.05555069446563721}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7760509252548218},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.706040620803833},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.592717707157135},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5882182121276855},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5829485654830933},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4001751244068146},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.34000587463378906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3007965683937073},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25865721702575684},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.13622862100601196},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08166924118995667},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.07321077585220337},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.05555069446563721},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc45484.2021.9682829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9682829","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 60th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W107583932","https://openalex.org/W1680579736","https://openalex.org/W1953057174","https://openalex.org/W2006498909","https://openalex.org/W2028678875","https://openalex.org/W2037450006","https://openalex.org/W2056257343","https://openalex.org/W2069350005","https://openalex.org/W2073787051","https://openalex.org/W2096450737","https://openalex.org/W2098432798","https://openalex.org/W2117355432","https://openalex.org/W2147032798","https://openalex.org/W2239232218","https://openalex.org/W2341171179","https://openalex.org/W2586680856","https://openalex.org/W2754517384","https://openalex.org/W2757446537","https://openalex.org/W2822752092","https://openalex.org/W2952063594","https://openalex.org/W2966348706","https://openalex.org/W3014366996","https://openalex.org/W3151532062","https://openalex.org/W3185475917","https://openalex.org/W4285719527","https://openalex.org/W6604362843","https://openalex.org/W6640881542","https://openalex.org/W6681631837","https://openalex.org/W6720923776","https://openalex.org/W6745072325","https://openalex.org/W6798615160"],"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/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"We":[0,12,82],"consider":[1],"the":[2,16,39,42,47,50,59,74,86,96,103],"problem":[3],"of":[4,24,32,49,105],"Reinforcement":[5],"Learning":[6],"for":[7,61],"nonlinear":[8],"stochastic":[9],"dynamical":[10],"systems.":[11],"show":[13,37,84],"that":[14,38,56,85,95],"in":[15,26,34,41,46,68,70,94,113],"RL":[17,114],"setting,":[18],"there":[19],"is":[20,55],"an":[21],"inherent":[22],"\"Curse":[23,31],"Variance\"":[25],"addition":[27],"to":[28,72,115],"Bellman\u2019s":[29],"infamous":[30],"Dimensionality\",":[33],"particular,":[35],"we":[36],"variance":[40,76],"solution":[43],"grows":[44],"factorial-exponentially":[45],"order":[48,71,98,107],"approximation.":[51],"A":[52],"fundamental":[53],"consequence":[54],"this":[57],"precludes":[58],"search":[60],"anything":[62],"other":[63],"than":[64],"\"local\"":[65],"feedback":[66],"solutions":[67],"RL,":[69],"control":[73,89],"explosive":[75],"growth,":[77],"and":[78],"thus,":[79],"ensure":[80],"accuracy.":[81],"further":[83],"deterministic":[87],"optimal":[88],"has":[90],"a":[91],"perturbation":[92],"structure,":[93],"higher":[97],"terms":[99],"do":[100],"not":[101],"affect":[102],"calculation":[104],"lower":[106],"terms,":[108],"which":[109],"can":[110],"be":[111],"utilized":[112],"get":[116],"accurate":[117],"local":[118],"solutions.":[119]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}