{"id":"https://openalex.org/W4309029392","doi":"https://doi.org/10.1137/21m1448185","title":"Exploratory HJB Equations and Their Convergence","display_name":"Exploratory HJB Equations and Their Convergence","publication_year":2022,"publication_date":"2022-11-11","ids":{"openalex":"https://openalex.org/W4309029392","doi":"https://doi.org/10.1137/21m1448185"},"language":"en","primary_location":{"id":"doi:10.1137/21m1448185","is_oa":false,"landing_page_url":"https://doi.org/10.1137/21m1448185","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/A5058487048","display_name":"Wenpin Tang","orcid":"https://orcid.org/0000-0001-7228-1954"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wenpin Tang","raw_affiliation_strings":["Department of Industrial Engineering and Operations Research, Columbia University, New York, NY USA 10027 (, )"],"raw_orcid":"https://orcid.org/0000-0001-7228-1954","affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Operations Research, Columbia University, New York, NY USA 10027 (, )","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041810986","display_name":"Yuming Paul Zhang","orcid":"https://orcid.org/0000-0002-2371-6840"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuming Paul Zhang","raw_affiliation_strings":["Department of Mathematics, University of California, San Diego, CA USA ()"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, University of California, San Diego, CA USA ()","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109487227","display_name":"Xun Yu Zhou","orcid":"https://orcid.org/0000-0003-0879-8400"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xun Yu Zhou","raw_affiliation_strings":["Department of Industrial Engineering and Operations Research, Columbia University, New York, NY USA 10027 (, )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Operations Research, Columbia University, New York, NY USA 10027 (, )","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5058487048"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":3.2877,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.93199737,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"60","issue":"6","first_page":"3191","last_page":"3216"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11829","display_name":"Mathematical Biology Tumor Growth","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2611","display_name":"Modeling and Simulation"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11829","display_name":"Mathematical Biology Tumor Growth","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2611","display_name":"Modeling and Simulation"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11520","display_name":"Advanced Thermodynamics and Statistical Mechanics","score":0.9830999970436096,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hamilton\u2013jacobi\u2013bellman-equation","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","score":0.7803901433944702},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.7418926358222961},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.6343413591384888},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5576726198196411},{"id":"https://openalex.org/keywords/viscosity-solution","display_name":"Viscosity solution","score":0.527167022228241},{"id":"https://openalex.org/keywords/stochastic-control","display_name":"Stochastic control","score":0.5073060393333435},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.49429798126220703},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4853614568710327},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.46123480796813965},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.33656930923461914}],"concepts":[{"id":"https://openalex.org/C196978813","wikidata":"https://www.wikidata.org/wiki/Q3302775","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","level":3,"score":0.7803901433944702},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.7418926358222961},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.6343413591384888},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5576726198196411},{"id":"https://openalex.org/C88731125","wikidata":"https://www.wikidata.org/wiki/Q7935676","display_name":"Viscosity solution","level":2,"score":0.527167022228241},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.5073060393333435},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.49429798126220703},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4853614568710327},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.46123480796813965},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.33656930923461914},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1137/21m1448185","is_oa":false,"landing_page_url":"https://doi.org/10.1137/21m1448185","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":[],"awards":[{"id":"https://openalex.org/G2366616776","display_name":null,"funder_award_id":"DMS-2206038","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7488619941","display_name":null,"funder_award_id":"DMS-2113779","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309111","display_name":"Columbia University","ror":"https://ror.org/00hj8s172"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W391985582","https://openalex.org/W1508267831","https://openalex.org/W1526719111","https://openalex.org/W1559997346","https://openalex.org/W1855169650","https://openalex.org/W1970195958","https://openalex.org/W1970790325","https://openalex.org/W1998575582","https://openalex.org/W2021290840","https://openalex.org/W2032316144","https://openalex.org/W2033812898","https://openalex.org/W2059103015","https://openalex.org/W2059736556","https://openalex.org/W2079184994","https://openalex.org/W2090255516","https://openalex.org/W2278678287","https://openalex.org/W2583356891","https://openalex.org/W2805963819","https://openalex.org/W2935248447","https://openalex.org/W2962788357","https://openalex.org/W3037286161","https://openalex.org/W3102782652","https://openalex.org/W3110347183","https://openalex.org/W3118228069","https://openalex.org/W3199075411","https://openalex.org/W4214597064","https://openalex.org/W4235758653","https://openalex.org/W4301074654"],"related_works":["https://openalex.org/W2358967034","https://openalex.org/W3153900688","https://openalex.org/W2962695587","https://openalex.org/W4301305831","https://openalex.org/W2754120543","https://openalex.org/W2963548356","https://openalex.org/W4306892756","https://openalex.org/W2094032802","https://openalex.org/W575255019","https://openalex.org/W1964620550"],"abstract_inverted_index":{".We":[0],"study":[1],"the":[2,9,30,42,47,51,56,59,64,70,80,85,116,139,143,156],"exploratory":[3,11,60,86],"Hamilton\u2013Jacobi\u2013Bellman":[4],"(HJB)":[5],"equation":[6],"arising":[7],"from":[8],"entropy-regularized":[10],"control":[12,61,67,88],"problem,":[13,89],"which":[14,90,148],"was":[15,91],"formulated":[16],"by":[17,93],"Wang,":[18],"Zariphopoulou,":[19],"and":[20,38,44,96,136],"Zhou":[21,97],"(J.":[22],"Mach.":[23],"Learn.":[24],"Res.,":[25],"21":[26],"(2020),":[27],"198)":[28],"in":[29,35,115],"context":[31,117],"of":[32,46,58,72,118,126,142],"reinforcement":[33],"learning":[34],"continuous":[36],"time":[37],"space.":[39],"We":[40,77,121],"establish":[41],"well-posedness":[43],"regularity":[45],"viscosity":[48],"solution":[49],"to":[50,63,75,84,106,134],"equation,":[52],"as":[53,55,131],"well":[54],"convergence":[57,127],"problem":[62,68,130],"classical":[65],"stochastic":[66],"when":[69],"level":[71],"exploration":[73,132],"decays":[74],"zero.":[76],"then":[78],"apply":[79],"general":[81],"results":[82],"obtained":[83],"temperature":[87,110],"introduced":[92],"Gao,":[94],"Xu,":[95],"(SIAM":[98],"J.":[99],"Control":[100],"Optim.,":[101],"60":[102],"(2022),":[103],"pp.":[104],"1250\u20131268)":[105],"design":[107],"an":[108,123],"endogenous":[109],"schedule":[111],"for":[112,128],"simulated":[113],"annealing":[114],"nonconvex":[119],"optimization.":[120],"derive":[122],"explicit":[124],"rate":[125],"this":[129],"diminishes":[133],"zero,":[135],"find":[137],"that":[138],"stationary":[140],"distribution":[141],"optimally":[144],"controlled":[145],"process":[146],"exists,":[147],"is":[149],"however":[150],"neither":[151],"a":[152,160],"Dirac":[153],"mass":[154],"on":[155],"global":[157],"optimum":[158],"nor":[159],"Gibbs":[161],"measure.KeywordsHJB":[162],"equationsstochastic":[163],"controlpartial":[164],"differential":[165],"equationsreinforcement":[166],"learningexploratory":[167],"controlentropy":[168],"regularizationsimulated":[169],"annealingoverdamped":[170],"Langevin":[171],"equationMSC":[172],"codes35F2160J6093E1593E20":[173]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}