{"id":"https://openalex.org/W3172288035","doi":null,"title":"Gradient Play in Multi-Agent Markov Stochastic Games: Stationary Points and Convergence","display_name":"Gradient Play in Multi-Agent Markov Stochastic Games: Stationary Points and Convergence","publication_year":2021,"publication_date":"2021-06-01","ids":{"openalex":"https://openalex.org/W3172288035","mag":"3172288035"},"language":"en","primary_location":{"id":"mag:3172288035","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.00198","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.00198","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102025389","display_name":"Runyu Cathy Zhang","orcid":"https://orcid.org/0000-0002-9333-3554","observed_orcids":["https://orcid.org/0000-0002-9333-3554"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Runyu Zhang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-9333-3554","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050464562","display_name":"Zhaolin Ren","orcid":"https://orcid.org/0009-0006-6502-6430","observed_orcids":["https://orcid.org/0009-0006-6502-6430","https://orcid.org/0009-0001-4608-4727"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaolin Ren","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0006-6502-6430","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100368048","display_name":"Na Li","orcid":"https://orcid.org/0000-0001-9545-3050","observed_orcids":["https://orcid.org/0000-0001-9545-3050"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Na Li","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-9545-3050","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7271000146865845,"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":0.7271000146865845,"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/T11031","display_name":"Game Theory and Applications","score":0.24400000274181366,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.00800000037997961,"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/multi-agent-markov-decision-process","display_name":"multi-agent Markov decision process","score":0.8659999966621399},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.8690000176429749},{"id":"https://openalex.org/keywords/stationary-policies","display_name":"stationary policies","score":0.6600000262260437},{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.6679999828338623},{"id":"https://openalex.org/keywords/epsilon-nash-equilibrium","display_name":"epsilon-Nash equilibrium","score":0.6769999861717224},{"id":"https://openalex.org/keywords/saddle-points","display_name":"saddle points","score":0.7409999966621399},{"id":"https://openalex.org/keywords/local-convergence","display_name":"local convergence","score":0.45500001311302185},{"id":"https://openalex.org/keywords/local-stability","display_name":"local stability","score":0.5929999947547913},{"id":"https://openalex.org/keywords/cooperative-multi-agent-reinforcement-learning","display_name":"cooperative multi-agent reinforcement learning","score":0.5450000166893005}],"concepts":[{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.6780561208724976},{"id":"https://openalex.org/C2681867","wikidata":"https://www.wikidata.org/wiki/Q690935","display_name":"Saddle point","level":2,"score":0.6421241760253906},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.6265098452568054},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5894826054573059},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5837982892990112},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5614426136016846},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.5119055509567261},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.49493831396102905},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.48304039239883423},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4771256446838379},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.4683489203453064},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4164137542247772},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3945419490337372},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3906000256538391},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.3469046354293823},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.17351576685905457},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12229719758033752},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.08547341823577881},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.06753945350646973},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3172288035","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.00198","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3172288035","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.00198","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1480046946","https://openalex.org/W1491494309","https://openalex.org/W1540725368","https://openalex.org/W1542941925","https://openalex.org/W1575592356","https://openalex.org/W1641379095","https://openalex.org/W1697075315","https://openalex.org/W1835254890","https://openalex.org/W1856231595","https://openalex.org/W1987083649","https://openalex.org/W2074621710","https://openalex.org/W2097532427","https://openalex.org/W2105643086","https://openalex.org/W2113702258","https://openalex.org/W2118247617","https://openalex.org/W2120846115","https://openalex.org/W2121863487","https://openalex.org/W2130937741","https://openalex.org/W2148808857","https://openalex.org/W2155027007","https://openalex.org/W2345652363","https://openalex.org/W2481762555","https://openalex.org/W2497473826","https://openalex.org/W2530849036","https://openalex.org/W2750605955","https://openalex.org/W2753984105","https://openalex.org/W2763081248","https://openalex.org/W2783637925","https://openalex.org/W2786479217","https://openalex.org/W2788115019","https://openalex.org/W2805324628","https://openalex.org/W2991046523","https://openalex.org/W2994779591","https://openalex.org/W3005335721","https://openalex.org/W3006882295","https://openalex.org/W3024652448","https://openalex.org/W3039845099","https://openalex.org/W3110309042","https://openalex.org/W3163894240"],"related_works":["https://openalex.org/W4394674309","https://openalex.org/W4312406920","https://openalex.org/W7133209712","https://openalex.org/W4226138304","https://openalex.org/W2964419277","https://openalex.org/W4393156376","https://openalex.org/W7133201764","https://openalex.org/W70059180","https://openalex.org/W4404313646","https://openalex.org/W1607392272"],"abstract_inverted_index":{"We":[0,65,170],"study":[1],"the":[2,5,54,104,121,135,160],"performance":[3],"of":[4,56,95,123,132,137,159],"gradient":[6],"play":[7],"algorithm":[8],"for":[9,92,180],"multi-agent":[10,96],"tabular":[11],"Markov":[12,99,148],"decision":[13],"processes":[14],"(MDPs),":[15],"which":[16,44,102],"are":[17,50,76,144,156,167],"also":[18,145,171],"known":[19],"as":[20,112],"stochastic":[21],"games":[22],"(SGs),":[23],"where":[24],"each":[25],"agent":[26],"tries":[27],"to":[28,89,125],"maximize":[29],"its":[30],"own":[31],"total":[32,161],"discounted":[33],"reward":[34],"by":[35,53],"making":[36],"decisions":[37],"independently":[38],"based":[39],"on":[40],"current":[41],"state":[42],"information":[43],"is":[45],"shared":[46],"between":[47],"agents.":[48,138],"Policies":[49],"directly":[51],"parameterized":[52],"probability":[55],"choosing":[57],"a":[58,62,83,93,173],"certain":[59],"action":[60],"at":[61],"given":[63],"state.":[64],"show":[66],"that":[67,120,153],"Nash":[68],"equilibria":[69],"(NEs)":[70],"and":[71,81,141,164],"first":[72],"order":[73],"stationary":[74],"policies":[75],"equivalent":[77],"in":[78],"this":[79],"setting,":[80],"give":[82,172],"non-asymptotic":[84],"global":[85],"convergence":[86,175],"rate":[87,176],"analysis":[88],"an":[90,113,127],"$\\epsilon$-NE":[91,128],"subclass":[94],"MDPs":[97],"called":[98],"potential":[100,149,162],"games,":[101,150],"includes":[103],"cooperative":[105],"setting":[106],"with":[107,134],"identical":[108],"rewards":[109],"among":[110],"agents":[111],"important":[114],"special":[115],"case.":[116],"Our":[117],"result":[118],"shows":[119],"number":[122,136],"iterations":[124],"reach":[126],"scales":[129],"linearly,":[130],"instead":[131],"exponentially,":[133],"Local":[139],"geometry":[140],"local":[142,157,174],"stability":[143],"considered.":[146],"For":[147],"we":[151],"prove":[152],"strict":[154,178],"NEs":[155,166,179],"maxima":[158],"function":[163],"fully-mixed":[165],"saddle":[168],"points.":[169],"around":[177],"more":[181],"general":[182],"settings.":[183]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2021-06-22T00:00:00"}