{"id":"https://openalex.org/W4213451050","doi":"https://doi.org/10.3390/a15030073","title":"Reinforcement Learning for Mean-Field Game","display_name":"Reinforcement Learning for Mean-Field Game","publication_year":2022,"publication_date":"2022-02-22","ids":{"openalex":"https://openalex.org/W4213451050","doi":"https://doi.org/10.3390/a15030073"},"language":"en","primary_location":{"id":"doi:10.3390/a15030073","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a15030073","pdf_url":"https://www.mdpi.com/1999-4893/15/3/73/pdf?version=1646100793","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-4893/15/3/73/pdf?version=1646100793","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111079060","display_name":"Mridul Agarwal","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mridul Agarwal","raw_affiliation_strings":["School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47907, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47907, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064822688","display_name":"Vaneet Aggarwal","orcid":"https://orcid.org/0000-0001-9131-4723"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vaneet Aggarwal","raw_affiliation_strings":["School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47907, USA","School of Industrial Engineering, Purdue University, West Lafayette, IN 47907, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47907, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"School of Industrial Engineering, Purdue University, West Lafayette, IN 47907, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022713299","display_name":"Arnob Ghosh","orcid":"https://orcid.org/0000-0003-0793-7536"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arnob Ghosh","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Ohio State University, Columbus, OH 43210, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Ohio State University, Columbus, OH 43210, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091814249","display_name":"Nilay Tiwari","orcid":null},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nilay Tiwari","raw_affiliation_strings":["Department of Electrical Engineering, I.I.T. Kanpur, Kanpur 208016, UP, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, I.I.T. Kanpur, Kanpur 208016, UP, India","institution_ids":["https://openalex.org/I94234084"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5064822688","https://openalex.org/A5111079060"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":0.4519,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.62897919,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"15","issue":"3","first_page":"73","last_page":"73"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12659","display_name":"Innovation Diffusion and Forecasting","score":0.9847000241279602,"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"}},"topics":[{"id":"https://openalex.org/T12659","display_name":"Innovation Diffusion and Forecasting","score":0.9847000241279602,"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/T11031","display_name":"Game Theory and Applications","score":0.983299970626831,"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/T11270","display_name":"Complex Systems and Time Series Analysis","score":0.9602000117301941,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8552975654602051},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6681953072547913},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5935142636299133},{"id":"https://openalex.org/keywords/fictitious-play","display_name":"Fictitious play","score":0.5122355818748474},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.46110233664512634},{"id":"https://openalex.org/keywords/sequential-game","display_name":"Sequential game","score":0.4477536380290985},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.4449208676815033},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.42685768008232117},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.426442414522171},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.42611610889434814},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.42370089888572693},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37340956926345825},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.34941697120666504},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.3243875503540039},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.2575835883617401},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25452327728271484},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10305759310722351},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09247547388076782}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8552975654602051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6681953072547913},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5935142636299133},{"id":"https://openalex.org/C145071142","wikidata":"https://www.wikidata.org/wiki/Q1411116","display_name":"Fictitious play","level":3,"score":0.5122355818748474},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.46110233664512634},{"id":"https://openalex.org/C73795354","wikidata":"https://www.wikidata.org/wiki/Q287618","display_name":"Sequential game","level":3,"score":0.4477536380290985},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.4449208676815033},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.42685768008232117},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.426442414522171},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.42611610889434814},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.42370089888572693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37340956926345825},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.34941697120666504},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.3243875503540039},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.2575835883617401},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25452327728271484},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10305759310722351},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09247547388076782},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/a15030073","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a15030073","pdf_url":"https://www.mdpi.com/1999-4893/15/3/73/pdf?version=1646100793","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:ef6c2bc7f2064d24bfdd2d11ffa62abd","is_oa":true,"landing_page_url":"https://doaj.org/article/ef6c2bc7f2064d24bfdd2d11ffa62abd","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms, Vol 15, Iss 3, p 73 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1999-4893/15/3/73/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/a15030073","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms; Volume 15; Issue 3; Pages: 73","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/a15030073","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a15030073","pdf_url":"https://www.mdpi.com/1999-4893/15/3/73/pdf?version=1646100793","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.44999998807907104,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1996399137","display_name":"CIF:  Small: Collaborative Research: Communications with Energy Harvesting Nodes","funder_award_id":"1527486","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3187085230","display_name":null,"funder_award_id":"CCF-1527486 and CNS-1618335.","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G5814912436","display_name":"NeTS: Small: Collaborative Research: Rethinking Erasure Codes for Cloud Storage: A Quantitative Framework for Latency, Reliability, and Cost Optimization","funder_award_id":"1618335","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/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4213451050.pdf","grobid_xml":"https://content.openalex.org/works/W4213451050.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W2107544712","https://openalex.org/W2120846115","https://openalex.org/W2131305292","https://openalex.org/W2145168954","https://openalex.org/W2158847403","https://openalex.org/W2916049220","https://openalex.org/W2921843114","https://openalex.org/W2962706750","https://openalex.org/W2962712206","https://openalex.org/W2963605646","https://openalex.org/W2965121598","https://openalex.org/W3123224094","https://openalex.org/W4297852499","https://openalex.org/W6631168379","https://openalex.org/W6678168664"],"related_works":["https://openalex.org/W4214835929","https://openalex.org/W4312141693","https://openalex.org/W1969185016","https://openalex.org/W4226086326","https://openalex.org/W1536009559","https://openalex.org/W2103821767","https://openalex.org/W2037619003","https://openalex.org/W2111030377","https://openalex.org/W2071306797","https://openalex.org/W3119014777"],"abstract_inverted_index":{"Stochastic":[0],"games":[1],"provide":[2],"a":[3,12,42,68,127,142],"framework":[4],"for":[5,131],"interactions":[6],"among":[7],"multiple":[8],"agents":[9,19,60,107],"and":[10,38,112,154,163],"enable":[11],"myriad":[13],"of":[14,30,59,92,100,103],"applications.":[15],"In":[16],"these":[17],"games,":[18],"decide":[20],"on":[21,66],"actions":[22],"simultaneously.":[23],"After":[24],"taking":[25],"an":[26,46,73,79,86,170],"action,":[27],"the":[28,35,57,90,93,97,101,104,109,120,135,146,152,159,164],"state":[29],"every":[31],"agent":[32,40,87,140],"updates":[33],"to":[34,118,158],"next":[36],"state,":[37],"each":[39,139],"receives":[41],"reward.":[43],"However,":[44],"finding":[45,67],"equilibrium":[47,70],"(if":[48],"exists)":[49],"in":[50,72,78,134],"this":[51],"game":[52,76],"is":[53,83],"often":[54],"difficult":[55],"when":[56],"number":[58],"becomes":[61],"large.":[62],"This":[63,124],"paper":[64,125],"focuses":[65],"mean-field":[69,136],"(MFE)":[71],"action-coupled":[74],"stochastic":[75],"setting":[77],"episodic":[80],"framework.":[81],"It":[82],"assumed":[84],"that":[85,151],"can":[88],"approximate":[89],"impact":[91],"other":[94],"agents\u2019":[95],"by":[96],"empirical":[98],"distribution":[99,111],"mean":[102],"actions.":[105],"All":[106],"know":[108],"action":[110,155],"employ":[113],"lower-myopic":[114],"best":[115],"response":[116],"dynamics":[117],"choose":[119],"optimal":[121,160],"oblivious":[122,161],"strategy.":[123],"proposes":[126],"posterior":[128],"sampling-based":[129],"approach":[130],"reinforcement":[132],"learning":[133],"game,":[137],"where":[138],"samples":[141],"transition":[143],"probability":[144],"from":[145],"previous":[147],"transitions.":[148],"We":[149],"show":[150],"policy":[153],"distributions":[156],"converge":[157],"strategy":[162],"limiting":[165],"distribution,":[166],"respectively,":[167],"which":[168],"constitute":[169],"MFE.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2022-02-25T00:00:00"}