{"id":"https://openalex.org/W3038093235","doi":"https://doi.org/10.1007/s00498-021-00310-1","title":"Unified reinforcement Q-learning for mean field game and control problems","display_name":"Unified reinforcement Q-learning for mean field game and control problems","publication_year":2022,"publication_date":"2022-01-15","ids":{"openalex":"https://openalex.org/W3038093235","doi":"https://doi.org/10.1007/s00498-021-00310-1","mag":"3038093235"},"language":"en","primary_location":{"id":"doi:10.1007/s00498-021-00310-1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00498-021-00310-1","pdf_url":null,"source":{"id":"https://openalex.org/S88345224","display_name":"Mathematics of Control Signals and Systems","issn_l":"0932-4194","issn":["0932-4194","1435-568X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Mathematics of Control, Signals, and Systems","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/A5079836831","display_name":"Andrea Angiuli","orcid":null},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrea Angiuli","raw_affiliation_strings":["Department of Statistics and Applied Probability, University of California, South Hall 5504, Santa Barbara, CA, 93106, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics and Applied Probability, University of California, South Hall 5504, Santa Barbara, CA, 93106, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051801244","display_name":"Jean\u2010Pierre Fouque","orcid":"https://orcid.org/0000-0001-8786-5645"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jean-Pierre Fouque","raw_affiliation_strings":["Department of Statistics and Applied Probability, University of California, South Hall 5504, Santa Barbara, CA, 93106, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics and Applied Probability, University of California, South Hall 5504, Santa Barbara, CA, 93106, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027824441","display_name":"Mathieu Lauri\u00e8re","orcid":"https://orcid.org/0000-0002-4380-1399"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mathieu Lauri\u00e8re","raw_affiliation_strings":["Department of Operations Research and Financial Engineering, Princeton University, Princeton, USA"],"raw_orcid":"https://orcid.org/0000-0002-4380-1399","affiliations":[{"raw_affiliation_string":"Department of Operations Research and Financial Engineering, Princeton University, Princeton, USA","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027824441"],"corresponding_institution_ids":["https://openalex.org/I20089843"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":7.3331,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.97631699,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"34","issue":"2","first_page":"217","last_page":"271"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10067","display_name":"Stochastic processes and financial applications","score":0.9979000091552734,"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":0.9979000091552734,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.978600025177002,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11520","display_name":"Advanced Thermodynamics and Statistical Mechanics","score":0.9769999980926514,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8500660061836243},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5527047514915466},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5517892837524414},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5333347916603088},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4958730638027191},{"id":"https://openalex.org/keywords/mean-field-theory","display_name":"Mean field theory","score":0.4714463949203491},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4632488489151001},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4467610716819763},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.443571001291275},{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.4386163353919983},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.43761178851127625},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43643954396247864},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4199557304382324},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.32668834924697876},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3240254521369934},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2791553735733032},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13274535536766052},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.08484798669815063}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8500660061836243},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5527047514915466},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5517892837524414},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5333347916603088},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4958730638027191},{"id":"https://openalex.org/C202213908","wikidata":"https://www.wikidata.org/wiki/Q626011","display_name":"Mean field theory","level":2,"score":0.4714463949203491},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4632488489151001},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4467610716819763},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.443571001291275},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.4386163353919983},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.43761178851127625},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43643954396247864},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4199557304382324},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.32668834924697876},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3240254521369934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2791553735733032},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13274535536766052},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.08484798669815063},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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:10.1007/s00498-021-00310-1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00498-021-00310-1","pdf_url":null,"source":{"id":"https://openalex.org/S88345224","display_name":"Mathematics of Control Signals and Systems","issn_l":"0932-4194","issn":["0932-4194","1435-568X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Mathematics of Control, Signals, and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W586490843","https://openalex.org/W1983321045","https://openalex.org/W2011000015","https://openalex.org/W2038686546","https://openalex.org/W2094364653","https://openalex.org/W2118686230","https://openalex.org/W2121863487","https://openalex.org/W2767550855","https://openalex.org/W2791784110","https://openalex.org/W2798579099","https://openalex.org/W2945395894","https://openalex.org/W2963605646","https://openalex.org/W2970875146","https://openalex.org/W2979330446","https://openalex.org/W2980452497","https://openalex.org/W2982138249","https://openalex.org/W2987018345","https://openalex.org/W2993562816","https://openalex.org/W2995725774","https://openalex.org/W2997345668","https://openalex.org/W3011120880","https://openalex.org/W3013079993","https://openalex.org/W3024682624","https://openalex.org/W3038093235","https://openalex.org/W3092283217","https://openalex.org/W3093413390","https://openalex.org/W3099043603","https://openalex.org/W3164756548","https://openalex.org/W3173500366","https://openalex.org/W4230008158","https://openalex.org/W4298044389","https://openalex.org/W6600474023","https://openalex.org/W6605991194","https://openalex.org/W6607794293","https://openalex.org/W6824100394","https://openalex.org/W6854636774"],"related_works":["https://openalex.org/W2123899227","https://openalex.org/W2937181779","https://openalex.org/W4206669594","https://openalex.org/W2104958792","https://openalex.org/W3133324912","https://openalex.org/W2383312578","https://openalex.org/W2542992786","https://openalex.org/W4310884706","https://openalex.org/W2610686804","https://openalex.org/W2123043338"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
