{"id":"https://openalex.org/W4410985964","doi":"https://doi.org/10.1109/tac.2025.3576379","title":"Independent and Decentralized Learning in Markov Potential Games","display_name":"Independent and Decentralized Learning in Markov Potential Games","publication_year":2025,"publication_date":"2025-06-03","ids":{"openalex":"https://openalex.org/W4410985964","doi":"https://doi.org/10.1109/tac.2025.3576379"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2025.3576379","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2025.3576379","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","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/A5031376831","display_name":"Chinmay Maheshwari","orcid":"https://orcid.org/0000-0003-3596-2851"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chinmay Maheshwari","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA, USA","department of Electrical Engineering and Computer Sciences at University of California Berkeley, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-3596-2851","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"department of Electrical Engineering and Computer Sciences at University of California Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103061454","display_name":"Manxi Wu","orcid":"https://orcid.org/0000-0001-5334-4163"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manxi Wu","raw_affiliation_strings":["Department of Civil and Environmental Engineering, University of California Berkeley, Berkeley, CA, USA","department of Civil and Environmental Engineering at University of California Berkeley, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5334-4163","affiliations":[{"raw_affiliation_string":"Department of Civil and Environmental Engineering, University of California Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"department of Civil and Environmental Engineering at University of California Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021764004","display_name":"Druv Pai","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Druv Pai","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA, USA","department of Electrical Engineering and Computer Sciences at University of California Berkeley, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0313-1551","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"department of Electrical Engineering and Computer Sciences at University of California Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103101043","display_name":"S. Shankar Sastry","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shankar Sastry","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA, USA","department of Electrical Engineering and Computer Sciences at University of California Berkeley, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"department of Electrical Engineering and Computer Sciences at University of California Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":1.8777,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.86554877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"70","issue":"11","first_page":"7538","last_page":"7553"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9714999794960022,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12288","display_name":"Optimization and Search Problems","score":0.9714999794960022,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12879","display_name":"Distributed Sensor Networks and Detection Algorithms","score":0.9559000134468079,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.929099977016449,"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/markov-chain","display_name":"Markov chain","score":0.6563793420791626},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5734654664993286},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5645381212234497},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4477453827857971},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.41862380504608154},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4135414659976959},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.38293030858039856},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.36512213945388794},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.30140724778175354},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24765127897262573},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11006057262420654}],"concepts":[{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.6563793420791626},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5734654664993286},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5645381212234497},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4477453827857971},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.41862380504608154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4135414659976959},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38293030858039856},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.36512213945388794},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30140724778175354},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24765127897262573},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11006057262420654}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2025.3576379","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2025.3576379","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F601216616","display_name":"Optimal","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1491706803","https://openalex.org/W1641379095","https://openalex.org/W1964757264","https://openalex.org/W1964886424","https://openalex.org/W2031452844","https://openalex.org/W2037067712","https://openalex.org/W2054314161","https://openalex.org/W2087486726","https://openalex.org/W2096145798","https://openalex.org/W2096913736","https://openalex.org/W2118247617","https://openalex.org/W2167957526","https://openalex.org/W2169077434","https://openalex.org/W2296599285","https://openalex.org/W2493056695","https://openalex.org/W2773381986","https://openalex.org/W2787689390","https://openalex.org/W2810102121","https://openalex.org/W2949597507","https://openalex.org/W2962990479","https://openalex.org/W2982316857","https://openalex.org/W3022321359","https://openalex.org/W3043098219","https://openalex.org/W3092557414","https://openalex.org/W4211095127","https://openalex.org/W4233696721","https://openalex.org/W4285092776","https://openalex.org/W4315488661","https://openalex.org/W4386120402","https://openalex.org/W4394674309"],"related_works":["https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2084326697","https://openalex.org/W2027903142","https://openalex.org/W2354322608","https://openalex.org/W2804608325","https://openalex.org/W2077211377","https://openalex.org/W2413828414","https://openalex.org/W2186675474"],"abstract_inverted_index":{"We":[0,18],"study":[1],"a":[2,91,106],"multi-agent":[3],"reinforcement":[4,89],"learning":[5,96,126],"dynamics,":[6],"and":[7,23,34],"analyze":[8],"its":[9],"asymptotic":[10],"behavior":[11],"in":[12,60,87],"infinite-horizon":[13],"discounted":[14],"Markov":[15],"potential":[16],"games.":[17],"focus":[19],"on":[20,55,78],"the":[21,31,56,79,84,110,122],"independent":[22],"decentralized":[24],"setting,":[25],"where":[26],"players":[27,42,65],"do":[28],"not":[29],"know":[30],"game":[32],"parameters,":[33],"cannot":[35],"communicate":[36],"or":[37],"coordinate.":[38],"In":[39],"each":[40],"stage,":[41],"update":[43,67,101],"their":[44,50,68,102],"estimate":[45],"of":[46,94,125],"Q-function":[47,103],"that":[48,99],"evaluates":[49],"total":[51],"contingent":[52],"payoff":[53],"based":[54,77],"realized":[57],"one-stage":[58,74],"reward":[59],"an":[61,72],"asynchronous":[62,116],"manner.":[63],"Then,":[64],"independently":[66],"policies":[69],"by":[70,83],"incorporating":[71],"optimal":[73],"deviation":[75],"strategy":[76],"estimated":[80],"Q-function.":[81],"Inspired":[82],"actor-critic":[85],"algorithm":[86],"single-agent":[88],"learning,":[90],"key":[92],"feature":[93],"our":[95],"dynamics":[97,127],"is":[98],"agents":[100],"estimates":[104],"at":[105],"faster":[107],"timescale":[108],"than":[109],"policies.":[111],"Leveraging":[112],"tools":[113],"from":[114],"two-timescale":[115],"stochastic":[117],"approximation":[118],"theory,":[119],"we":[120],"characterize":[121],"convergent":[123],"set":[124]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}