{"id":"https://openalex.org/W4394674309","doi":"https://doi.org/10.1109/tac.2024.3387208","title":"Gradient Play in Stochastic Games: Stationary Points, Convergence, and Sample Complexity","display_name":"Gradient Play in Stochastic Games: Stationary Points, Convergence, and Sample Complexity","publication_year":2024,"publication_date":"2024-04-10","ids":{"openalex":"https://openalex.org/W4394674309","doi":"https://doi.org/10.1109/tac.2024.3387208"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2024.3387208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2024.3387208","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/A5102025389","display_name":"Runyu Zhang","orcid":"https://orcid.org/0000-0002-9333-3554"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Runyu Zhang","raw_affiliation_strings":["Harvard School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-9333-3554","affiliations":[{"raw_affiliation_string":"Harvard School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050464562","display_name":"Zhaolin Ren","orcid":"https://orcid.org/0009-0006-6502-6430"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaolin Ren","raw_affiliation_strings":["Harvard School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0009-0006-6502-6430","affiliations":[{"raw_affiliation_string":"Harvard School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100368048","display_name":"Na Li","orcid":"https://orcid.org/0000-0001-9545-3050"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Na Li","raw_affiliation_strings":["Harvard School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0001-9545-3050","affiliations":[{"raw_affiliation_string":"Harvard School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I136199984"],"apc_list":null,"apc_paid":null,"fwci":3.3876,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.92099366,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"69","issue":"10","first_page":"6499","last_page":"6514"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.9990000128746033,"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":0.9990000128746033,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9958999752998352,"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/parameterized-complexity","display_name":"Parameterized complexity","score":0.6260348558425903},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5641821622848511},{"id":"https://openalex.org/keywords/saddle-point","display_name":"Saddle point","score":0.5395879149436951},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5309091806411743},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5258679389953613},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.45204100012779236},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4503372013568878},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.45031264424324036},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.43643227219581604},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.4300847053527832},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.42849984765052795},{"id":"https://openalex.org/keywords/stationary-point","display_name":"Stationary point","score":0.42406025528907776},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.37188437581062317},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3295438289642334},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.31741076707839966},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14181450009346008},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10643193125724792},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.0886196494102478}],"concepts":[{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.6260348558425903},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5641821622848511},{"id":"https://openalex.org/C2681867","wikidata":"https://www.wikidata.org/wiki/Q690935","display_name":"Saddle point","level":2,"score":0.5395879149436951},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5309091806411743},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5258679389953613},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.45204100012779236},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4503372013568878},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.45031264424324036},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.43643227219581604},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.4300847053527832},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.42849984765052795},{"id":"https://openalex.org/C189237950","wikidata":"https://www.wikidata.org/wiki/Q2500758","display_name":"Stationary point","level":2,"score":0.42406025528907776},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.37188437581062317},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3295438289642334},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.31741076707839966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14181450009346008},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10643193125724792},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0886196494102478},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2024.3387208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2024.3387208","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W206679605","https://openalex.org/W1488556245","https://openalex.org/W1491494309","https://openalex.org/W1540725368","https://openalex.org/W1641379095","https://openalex.org/W1987083649","https://openalex.org/W2043635114","https://openalex.org/W2074621710","https://openalex.org/W2096145798","https://openalex.org/W2097532427","https://openalex.org/W2103294258","https://openalex.org/W2105643086","https://openalex.org/W2107544712","https://openalex.org/W2113702258","https://openalex.org/W2120846115","https://openalex.org/W2130937741","https://openalex.org/W2132580642","https://openalex.org/W2148808857","https://openalex.org/W2176451521","https://openalex.org/W2481762555","https://openalex.org/W2763081248","https://openalex.org/W2962990479","https://openalex.org/W2968526727","https://openalex.org/W2969419629","https://openalex.org/W2991046523","https://openalex.org/W3006882295","https://openalex.org/W3105688066","https://openalex.org/W3122272342","https://openalex.org/W3163894240","https://openalex.org/W3207876914","https://openalex.org/W3209754935","https://openalex.org/W3213818741","https://openalex.org/W4230826215","https://openalex.org/W4251525635","https://openalex.org/W4254547512","https://openalex.org/W4288269457","https://openalex.org/W4298314778","https://openalex.org/W4301501993","https://openalex.org/W4389775604","https://openalex.org/W4394674309","https://openalex.org/W6600018571","https://openalex.org/W6634413486","https://openalex.org/W6674705169","https://openalex.org/W6675811377","https://openalex.org/W6678168664","https://openalex.org/W6679903357","https://openalex.org/W6683204974","https://openalex.org/W6728155968","https://openalex.org/W6743367460","https://openalex.org/W6744562401","https://openalex.org/W6748721451","https://openalex.org/W6749032143","https://openalex.org/W6754906582","https://openalex.org/W6758937863","https://openalex.org/W6762982123","https://openalex.org/W6771232374","https://openalex.org/W6776824048","https://openalex.org/W6780486084","https://openalex.org/W6785161469","https://openalex.org/W6791976426","https://openalex.org/W6796527454","https://openalex.org/W6802197776","https://openalex.org/W6802528643","https://openalex.org/W6809591387","https://openalex.org/W6810414227"],"related_works":["https://openalex.org/W2002852249","https://openalex.org/W1751422738","https://openalex.org/W2087951380","https://openalex.org/W2170040487","https://openalex.org/W4402475112","https://openalex.org/W2312509642","https://openalex.org/W2336318624","https://openalex.org/W2978731891","https://openalex.org/W1979925556","https://openalex.org/W2592651140"],"abstract_inverted_index":{"We":[0,56],"study":[1],"the":[2,5,45,92,131,149,171],"performance":[3],"of":[4,47,84,133,146,151,170],"gradient":[6,120],"play":[7,121],"algorithm":[8,108],"for":[9,81,117],"stochastic":[10],"games":[11,89],"(SGs),":[12],"where":[13,161],"each":[14],"agent":[15],"tries":[16],"to":[17,135],"maximize":[18],"its":[19],"own":[20],"total":[21,172],"discounted":[22],"reward":[23],"by":[24,44],"making":[25],"decisions":[26],"<italic":[27],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[28,139],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">independently</i>":[29],"based":[30],"on":[31],"current":[32],"state":[33],"information":[34],"which":[35],"is":[36],"shared":[37],"between":[38],"agents.":[39,152],"Policies":[40],"are":[41,66,158,167,178],"directly":[42],"parameterized":[43],"probability":[46],"choosing":[48],"a":[49,53,73,82,104,111],"certain":[50],"action":[51],"at":[52],"given":[54],"state.":[55],"show":[57],"that":[58,130,164],"Nash":[59],"equilibria":[60],"(NEs)":[61],"and":[62,71,109,122,155,175],"first-order":[63],"stationary":[64],"policies":[65],"equivalent":[67],"in":[68],"this":[69],"setting,":[70],"give":[72,110],"local":[74,156,168],"convergence":[75,114],"rate":[76,115],"around":[77],"strict":[78,165],"NEs.":[79],"Further,":[80],"subclass":[83],"SGs":[85],"called":[86],"Markov":[87],"potential":[88,173],"(which":[90],"includes":[91],"setting":[93],"with":[94,148],"identical":[95],"rewards":[96],"as":[97],"an":[98,137],"important":[99],"special":[100],"case),":[101],"we":[102,162],"design":[103],"sample-based":[105,124],"reinforcement":[106],"learning":[107,125],"non-asymptotic":[112],"global":[113],"analysis":[116],"both":[118],"exact":[119],"our":[123],"algorithm.":[126],"Our":[127],"result":[128],"shows":[129],"number":[132,150],"iterations":[134],"reach":[136],"<inline-formula":[138],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[140],"notation=\"LaTeX\">$\\epsilon$</tex-math></inline-formula>":[141],"-NE":[142],"scales":[143],"linearly,":[144],"instead":[145],"exponentially,":[147],"Local":[153],"geometry":[154],"stability":[157],"also":[159],"considered,":[160],"prove":[163],"NEs":[166,177],"maxima":[169],"function":[174],"fully-mixed":[176],"saddle":[179],"points.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}