{"id":"https://openalex.org/W4407949096","doi":"https://doi.org/10.1109/cdc56724.2024.10885842","title":"Independent Policy Mirror Descent for Markov Potential Games: Scaling to Large Number of Players","display_name":"Independent Policy Mirror Descent for Markov Potential Games: Scaling to Large Number of Players","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4407949096","doi":"https://doi.org/10.1109/cdc56724.2024.10885842"},"language":"en","primary_location":{"id":"doi:10.1109/cdc56724.2024.10885842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10885842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5058216725","display_name":"Pragnya Alatur","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Pragnya Alatur","raw_affiliation_strings":["ETH Zurich,department of Computer Science,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich,department of Computer Science,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094229975","display_name":"Anas Barakat","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Anas Barakat","raw_affiliation_strings":["ETH Zurich,department of Computer Science,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich,department of Computer Science,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071683073","display_name":"Niao He","orcid":"https://orcid.org/0000-0003-4225-7536"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Niao He","raw_affiliation_strings":["ETH Zurich,department of Computer Science,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich,department of Computer Science,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3883","last_page":"3888"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.7885000109672546,"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/T11031","display_name":"Game Theory and Applications","score":0.7885000109672546,"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/T13825","display_name":"Economic Policies and Impacts","score":0.7803999781608582,"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/scaling","display_name":"Scaling","score":0.6263007521629333},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.6072897911071777},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6051737070083618},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5522435307502747},{"id":"https://openalex.org/keywords/descent","display_name":"Descent (aeronautics)","score":0.43399202823638916},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3417515456676483},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25401604175567627},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.15897181630134583},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13952556252479553},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09290573000907898},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.05673500895500183}],"concepts":[{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.6263007521629333},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.6072897911071777},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6051737070083618},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5522435307502747},{"id":"https://openalex.org/C2776637919","wikidata":"https://www.wikidata.org/wiki/Q624380","display_name":"Descent (aeronautics)","level":2,"score":0.43399202823638916},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3417515456676483},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25401604175567627},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.15897181630134583},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13952556252479553},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09290573000907898},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.05673500895500183},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc56724.2024.10885842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10885842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2002373723","https://openalex.org/W2169077434","https://openalex.org/W2752505153","https://openalex.org/W3022321359","https://openalex.org/W3127686539","https://openalex.org/W4249667877","https://openalex.org/W4312406920","https://openalex.org/W4315471814","https://openalex.org/W4315488661","https://openalex.org/W4372341159","https://openalex.org/W4381739798","https://openalex.org/W4389775604","https://openalex.org/W4391020260","https://openalex.org/W6796527454","https://openalex.org/W6802197776","https://openalex.org/W6802528643","https://openalex.org/W6809591387","https://openalex.org/W6809872370","https://openalex.org/W6810414227","https://openalex.org/W6838604868","https://openalex.org/W6851297555","https://openalex.org/W6857463059","https://openalex.org/W6875724022"],"related_works":["https://openalex.org/W2486267010","https://openalex.org/W4298096494","https://openalex.org/W1678820847","https://openalex.org/W2559216629","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W4236062181","https://openalex.org/W2367222340"],"abstract_inverted_index":{"Markov":[0,9],"Potential":[1],"Games":[2],"(MPGs)":[3],"form":[4],"an":[5,117],"important":[6,64],"sub-class":[7],"of":[8,45,54,105,116,147,165,168],"games,":[10],"which":[11],"are":[12],"a":[13,27,51,140],"common":[14],"framework":[15],"to":[16,50,79,83],"model":[17],"multi-agent":[18,59],"reinforcement":[19],"learning":[20,48,71],"problems.":[21],"In":[22,88,108],"particular,":[23],"MPGs":[24],"include":[25],"as":[26,135],"special":[28],"case":[29],"the":[30,35,38,43,69,93,103,113,145,159,166,169],"identical-interest":[31],"setting":[32,72],"where":[33,73],"all":[34],"agents":[36,55,74,106],"share":[37],"same":[39],"reward":[40],"function.":[41],"Scaling":[42],"performance":[44],"Nash":[46],"equilibrium":[47],"algorithms":[49],"large":[52],"number":[53,104,146],"is":[56,162],"crucial":[57],"for":[58,96,124],"systems.":[60],"To":[61],"address":[62],"this":[63,109],"challenge,":[65],"we":[66,111],"focus":[67],"on":[68,91,144],"independent":[70,118,164],"can":[75],"only":[76],"have":[77],"access":[78],"their":[80,85],"local":[81],"information":[82],"update":[84],"own":[86],"policy.":[87],"prior":[89,156],"work":[90],"MPGs,":[92],"iteration":[94,114,160],"complexity":[95,115,161],"obtaining":[97],"$\\varepsilon$-Nash":[98],"regret":[99],"scales":[100],"linearly":[101],"with":[102,130,152],"N.":[107],"work,":[110],"investigate":[112],"policy":[119,137],"mirror":[120],"descent":[121],"(PMD)":[122],"algorithm":[123],"MPGs.":[125],"We":[126],"show":[127],"that":[128],"PMD":[129,151],"KL":[131],"regularization,":[132],"also":[133,163],"known":[134],"natural":[136],"gradient,":[138],"enjoys":[139],"better":[141],"$\\sqrt{N}$":[142],"dependence":[143],"agents,":[148],"improving":[149],"over":[150],"Euclidean":[153],"regularization":[154],"and":[155],"work.":[157],"Furthermore,":[158],"sizes":[167],"agents\u2019":[170],"action":[171],"spaces.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}