{"id":"https://openalex.org/W7123344895","doi":"https://doi.org/10.1109/cdc57313.2025.11312444","title":"Population-aware Online Mirror Descent for Mean-Field Games with Common Noise by Deep Reinforcement Learning","display_name":"Population-aware Online Mirror Descent for Mean-Field Games with Common Noise by Deep Reinforcement Learning","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7123344895","doi":"https://doi.org/10.1109/cdc57313.2025.11312444"},"language":null,"primary_location":{"id":"doi:10.1109/cdc57313.2025.11312444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th 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/A5109347759","display_name":"Zida Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799798094"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zida Wu","raw_affiliation_strings":["UCLA"],"affiliations":[{"raw_affiliation_string":"UCLA","institution_ids":["https://openalex.org/I2799798094"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mathieu Lauriere","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mathieu Lauriere","raw_affiliation_strings":["New York University Shanghai"],"affiliations":[{"raw_affiliation_string":"New York University Shanghai","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Matthieu Geist","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthieu Geist","raw_affiliation_strings":["Earth Species Project"],"affiliations":[{"raw_affiliation_string":"Earth Species Project","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122883935","display_name":"Olivier Pietquin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Olivier Pietquin","raw_affiliation_strings":["Earth Species Project"],"affiliations":[{"raw_affiliation_string":"Earth Species Project","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108702721","display_name":"Ankur Mehta","orcid":null},"institutions":[{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799798094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ankur Mehta","raw_affiliation_strings":["UCLA"],"affiliations":[{"raw_affiliation_string":"UCLA","institution_ids":["https://openalex.org/I2799798094"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5109347759"],"corresponding_institution_ids":["https://openalex.org/I2799798094"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.83808236,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6338","last_page":"6345"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8665000200271606,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8665000200271606,"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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.03970000147819519,"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"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.013799999840557575,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.6243000030517578},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6136000156402588},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6119999885559082},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.5551999807357788},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5210999846458435},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.4945000112056732},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4404999911785126},{"id":"https://openalex.org/keywords/fictitious-play","display_name":"Fictitious play","score":0.43709999322891235}],"concepts":[{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.6243000030517578},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6136000156402588},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6119999885559082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.607699990272522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5867000222206116},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.5551999807357788},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5210999846458435},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4945000112056732},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4404999911785126},{"id":"https://openalex.org/C145071142","wikidata":"https://www.wikidata.org/wiki/Q1411116","display_name":"Fictitious play","level":3,"score":0.43709999322891235},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3833000063896179},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3327000141143799},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31209999322891235},{"id":"https://openalex.org/C2776637919","wikidata":"https://www.wikidata.org/wiki/Q624380","display_name":"Descent (aeronautics)","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.288100004196167},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.28700000047683716},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C32407928","wikidata":"https://www.wikidata.org/wiki/Q2733833","display_name":"Best response","level":3,"score":0.2759999930858612},{"id":"https://openalex.org/C2986577269","wikidata":"https://www.wikidata.org/wiki/Q11306265","display_name":"Random noise","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C31084985","wikidata":"https://www.wikidata.org/wiki/Q372650","display_name":"Common knowledge (logic)","level":5,"score":0.26190000772476196},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc57313.2025.11312444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6326093673706055}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Mean":[0],"Field":[1],"Games":[2],"(MFGs)":[3],"offer":[4],"a":[5,20,107],"powerful":[6],"framework":[7],"for":[8,113],"studying":[9],"large-scale":[10],"multi-agent":[11],"systems.":[12],"Yet,":[13],"learning":[14,48],"Nash":[15,55],"equilibria":[16,56],"in":[17,118],"MFGs":[18],"remains":[19],"challenging":[21],"problem,":[22],"particularly":[23,106],"when":[24,31],"the":[25,32,119,125],"initial":[26,79],"distribution":[27],"is":[28,34,75],"unknown":[29],"or":[30,61],"population":[33],"subject":[35],"to":[36,52,77,103],"common":[37,84,122],"noise.":[38,85],"In":[39],"this":[40],"paper,":[41],"we":[42,93],"introduce":[43],"an":[44],"efficient":[45],"deep":[46],"reinforcement":[47],"(DRL)":[49],"algorithm":[50,97],"designed":[51],"achieve":[53],"population-dependent":[54,114],"without":[57],"relying":[58],"on":[59,89],"averaging":[60],"historical":[62],"sampling,":[63],"inspired":[64],"by":[65],"Munchausen":[66],"RL":[67],"and":[68,81,127],"Online":[69],"Mirror":[70],"Descent.":[71],"The":[72,116],"resulting":[73],"policy":[74],"adaptable":[76],"various":[78],"distributions":[80],"sources":[82],"of":[83,110,121,129],"Through":[86],"numerical":[87],"experiments":[88],"seven":[90],"canonical":[91],"examples,":[92],"demonstrate":[94],"that":[95],"our":[96,130],"exhibits":[98],"superior":[99],"convergence":[100],"properties":[101],"compared":[102],"state-of-the-art":[104],"algorithms,":[105],"DRL":[108],"version":[109],"Fictitious":[111],"Play":[112],"policies.":[115],"performance":[117],"presence":[120],"noise":[123],"underscores":[124],"robustness":[126],"adaptability":[128],"approach.":[131]},"counts_by_year":[],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2026-01-14T00:00:00"}