{"id":"https://openalex.org/W7213354977","doi":"https://doi.org/10.48550/arxiv.2609.14972","title":"Learning to Solve Stochastic Controls with Unknown Drifts and Running Rewards: Theory, Algorithms and Convergence","display_name":"Learning to Solve Stochastic Controls with Unknown Drifts and Running Rewards: Theory, Algorithms and Convergence","publication_year":2026,"publication_date":"2026-09-14","ids":{"openalex":"https://openalex.org/W7213354977","doi":"https://doi.org/10.48550/arxiv.2609.14972"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.14972","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.14972","pdf_url":"https://arxiv.org/pdf/2609.14972","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.14972","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5151750584","display_name":"Jin Ma","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ma, Jin","raw_affiliation_strings":["Department of Mathematics , University of Southern California , Los Angeles , CA 90089 ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics , University of Southern California , Los Angeles , CA 90089 ;","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059852563","display_name":"Gaozhan Wang","orcid":"https://orcid.org/0009-0000-8795-8366","observed_orcids":["https://orcid.org/0009-0000-8795-8366","https://orcid.org/0000-0002-2781-7593"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Gaozhan","raw_affiliation_strings":["Department of Mathematics , University of Southern California , Los Angeles , CA 90089 ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics , University of Southern California , Los Angeles , CA 90089 ;","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374699","display_name":"Jianfeng Zhang","orcid":"https://orcid.org/0000-0001-7218-6383","observed_orcids":["https://orcid.org/0000-0001-7218-6383","https://orcid.org/0009-0006-9280-1500"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Jianfeng","raw_affiliation_strings":["Department of Mathematics , University of Southern California , Los Angeles , CA 90089 ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics , University of Southern California , Los Angeles , CA 90089 ;","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5151842543","display_name":"Xunyu Zhou","orcid":null,"observed_orcids":[]},"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":"Zhou, Xunyu","raw_affiliation_strings":["Department of Industrial Engineering and Operations Research , Columbia University , New York , NY 10027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Operations Research , Columbia University , New York , NY 10027","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10067","display_name":"Stochastic processes and financial applications","score":0.7929999828338623,"subfield":{"id":"https://openalex.org/subfields/2003","display_name":"Finance"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10067","display_name":"Stochastic processes and financial applications","score":0.7929999828338623,"subfield":{"id":"https://openalex.org/subfields/2003","display_name":"Finance"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.18709999322891235,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.016499999910593033,"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/stochastic-control","display_name":"stochastic control","score":0.7599999904632568},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.5680000185966492},{"id":"https://openalex.org/keywords/relaxed-controls","display_name":"relaxed controls","score":0.6859999895095825},{"id":"https://openalex.org/keywords/entropy-regularization","display_name":"entropy regularization","score":0.9980000257492065},{"id":"https://openalex.org/keywords/optimal-value-function","display_name":"optimal value function","score":0.6859999895095825},{"id":"https://openalex.org/keywords/hamilton-jacobi-bellman-equation","display_name":"Hamilton-Jacobi-Bellman equation","score":0.7160000205039978},{"id":"https://openalex.org/keywords/policy-iteration","display_name":"policy iteration","score":0.8100000023841858},{"id":"https://openalex.org/keywords/convergence-analysis","display_name":"convergence analysis","score":0.8080000281333923},{"id":"https://openalex.org/keywords/high-dimensional-control","display_name":"high-dimensional control","score":0.6159999966621399},{"id":"https://openalex.org/keywords/continuous-time-control","display_name":"continuous-time control","score":0.6240000128746033},{"id":"https://openalex.org/keywords/probabilistic-representation","display_name":"probabilistic representation","score":0.5550000071525574},{"id":"https://openalex.org/keywords/fixed-point-analysis","display_name":"fixed-point analysis","score":0.44699999690055847}],"concepts":[{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5756000280380249},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5555999875068665},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5554999709129333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.552299976348877},{"id":"https://openalex.org/C203616005","wikidata":"https://www.wikidata.org/wiki/Q620495","display_name":"Hessian matrix","level":2,"score":0.5472000241279602},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5253999829292297},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5149999856948853},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.48809999227523804},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4415999948978424},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4277999997138977},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.4253999888896942},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.42250001430511475},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4077000021934509},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.39809998869895935},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.37709999084472656},{"id":"https://openalex.org/C196978813","wikidata":"https://www.wikidata.org/wiki/Q3302775","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","level":3,"score":0.3700000047683716},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.35269999504089355},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.3271999955177307},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.3246999979019165},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C95763700","wikidata":"https://www.wikidata.org/wiki/Q578985","display_name":"Convergence of random variables","level":3,"score":0.26260000467300415},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.2524999976158142}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.14972","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.14972","pdf_url":"https://arxiv.org/pdf/2609.14972","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.14972","doi":"https://doi.org/10.48550/arxiv.2609.14972","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.14972","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.14972","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.14972","pdf_url":"https://arxiv.org/pdf/2609.14972","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1493895020","display_name":"Some New Perspectives on Stochastic Games/Controls, and Their Learning","funder_award_id":"2510403","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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213354977.pdf","grobid_xml":"https://content.openalex.org/works/W7213354977.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W4402519509","https://openalex.org/W4405486670","https://openalex.org/W4414285019","https://openalex.org/W4414876888","https://openalex.org/W4415332651","https://openalex.org/W6884998335","https://openalex.org/W7127899083","https://openalex.org/W7134236372","https://openalex.org/W7155546644","https://openalex.org/W7161982504","https://openalex.org/W7164316200","https://openalex.org/W7165849537"],"related_works":["https://openalex.org/W2166356462","https://openalex.org/W3202828523","https://openalex.org/W4408535468","https://openalex.org/W4311970251","https://openalex.org/W3108003339","https://openalex.org/W4391673127","https://openalex.org/W7138869816","https://openalex.org/W4255064568","https://openalex.org/W4414285487","https://openalex.org/W4399144941"],"abstract_inverted_index":{"We":[0,138],"study":[1,151],"continuous-time":[2],"and":[3,12,35,40,51,69,93,121,135],"possibly":[4],"high-dimensional":[5],"stochastic":[6],"control":[7,73],"problems":[8],"where":[9,157],"drift":[10],"coefficients":[11,78],"running":[13],"reward":[14],"functions":[15,61],"are":[16],"unknown.":[17],"Due":[18],"to":[19,46,55,127],"these":[20],"missing":[21],"model":[22],"primitives,":[23],"we":[24,83,150],"take":[25],"the":[26,58,65,76,89,105,109,128,140,161],"exploratory,":[27],"reinforcement":[28],"learning":[29],"(RL)":[30],"framework":[31],"of":[32,87,108,130,142,160],"Wang,":[33],"Zariphopoulou,":[34],"Zhou(2020)":[36],"with":[37],"relaxed":[38],"controls":[39],"entropy":[41],"regularization.":[42],"The":[43],"objective":[44],"is":[45,163],"develop":[47],"theoretically":[48],"grounded,":[49],"efficient":[50],"scalable":[52],"RL":[53],"algorithms":[54,134,144],"learn":[56],"both":[57,88],"optimal":[59,70,90],"value":[60,91],"(which":[62],"also":[63],"solve":[64],"exploratory":[66,71],"HJB":[67],"equation)":[68],"feedback":[72],"policies.":[74],"When":[75],"diffusion":[77,106,155],"do":[79],"not":[80],"contain":[81],"control,":[82],"employ":[84],"probabilistic":[85],"representations":[86],"function":[92],"its":[94],"gradient":[95],"based":[96],"on":[97,104,116],"an":[98],"auxiliary":[99],"state":[100],"process":[101],"depending":[102],"only":[103],"part":[107],"original":[110],"dynamics.":[111],"With":[112],"a":[113,152],"delicate":[114],"analysis":[115],"some":[117],"properly":[118],"defined":[119],"mappings":[120],"their":[122,136],"fixed":[123],"points,":[124],"this":[125],"leads":[126],"introduction":[129],"our":[131,143],"policy":[132],"iteration":[133],"convergence.":[137],"demonstrate":[139],"performance":[141],"through":[145],"various":[146],"numerical":[147],"examples.":[148],"Finally,":[149],"special":[153],"control-dependent":[154],"case":[156],"probability":[158],"representation":[159],"Hessian":[162],"called":[164],"for.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-16T00:00:00"}