{"id":"https://openalex.org/W3006882295","doi":"https://doi.org/10.1137/18m1231298","title":"On Gradient-Based Learning in Continuous Games","display_name":"On Gradient-Based Learning in Continuous Games","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3006882295","doi":"https://doi.org/10.1137/18m1231298","mag":"3006882295"},"language":"en","primary_location":{"id":"doi:10.1137/18m1231298","is_oa":true,"landing_page_url":"https://doi.org/10.1137/18m1231298","pdf_url":"https://epubs.siam.org/doi/pdf/10.1137/18M1231298","source":{"id":"https://openalex.org/S4210229561","display_name":"SIAM Journal on Mathematics of Data Science","issn_l":"2577-0187","issn":["2577-0187"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Mathematics of Data Science","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://epubs.siam.org/doi/pdf/10.1137/18M1231298","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Eric Mazumdar","orcid":"https://orcid.org/0000-0002-1815-269X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Eric Mazumdar","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lillian J. Ratliff","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lillian J. Ratliff","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"S. Shankar Sastry","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S. Shankar Sastry","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.7094,"has_fulltext":false,"cited_by_count":69,"citation_normalized_percentile":{"value":0.96676593,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"2","issue":"1","first_page":"103","last_page":"131"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.4212999939918518,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.4212999939918518,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.2199999988079071,"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":0.12160000205039978,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6858000159263611},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.6694999933242798},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5777999758720398},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5555999875068665},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5138000249862671},{"id":"https://openalex.org/keywords/fictitious-play","display_name":"Fictitious play","score":0.4803999960422516},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4657999873161316},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.429500013589859},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.4259999990463257},{"id":"https://openalex.org/keywords/best-response","display_name":"Best response","score":0.42250001430511475}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6858000159263611},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.6694999933242798},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6230000257492065},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5777999758720398},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5555999875068665},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5138000249862671},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48969998955726624},{"id":"https://openalex.org/C145071142","wikidata":"https://www.wikidata.org/wiki/Q1411116","display_name":"Fictitious play","level":3,"score":0.4803999960422516},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4657999873161316},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.429500013589859},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.4259999990463257},{"id":"https://openalex.org/C32407928","wikidata":"https://www.wikidata.org/wiki/Q2733833","display_name":"Best response","level":3,"score":0.42250001430511475},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.39649999141693115},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37929999828338623},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.36880001425743103},{"id":"https://openalex.org/C50318809","wikidata":"https://www.wikidata.org/wiki/Q2145081","display_name":"Replicator equation","level":3,"score":0.33730000257492065},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.3158000111579895},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3140000104904175},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C79379906","wikidata":"https://www.wikidata.org/wiki/Q3174497","display_name":"Dynamical systems theory","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C88959737","wikidata":"https://www.wikidata.org/wiki/Q1546627","display_name":"Strategy","level":3,"score":0.29440000653266907},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C73795354","wikidata":"https://www.wikidata.org/wiki/Q287618","display_name":"Sequential game","level":3,"score":0.27489998936653137},{"id":"https://openalex.org/C2779251273","wikidata":"https://www.wikidata.org/wiki/Q43436","display_name":"Pearl","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C2776637919","wikidata":"https://www.wikidata.org/wiki/Q624380","display_name":"Descent (aeronautics)","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C146930158","wikidata":"https://www.wikidata.org/wiki/Q656416","display_name":"Extensive-form game","level":4,"score":0.2623000144958496},{"id":"https://openalex.org/C202556891","wikidata":"https://www.wikidata.org/wiki/Q1584646","display_name":"Repeated game","level":3,"score":0.25839999318122864},{"id":"https://openalex.org/C22171661","wikidata":"https://www.wikidata.org/wiki/Q1074380","display_name":"Stochastic game","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C164407509","wikidata":"https://www.wikidata.org/wiki/Q5384490","display_name":"Equilibrium selection","level":4,"score":0.25110000371932983}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1137/18m1231298","is_oa":true,"landing_page_url":"https://doi.org/10.1137/18m1231298","pdf_url":"https://epubs.siam.org/doi/pdf/10.1137/18M1231298","source":{"id":"https://openalex.org/S4210229561","display_name":"SIAM Journal on Mathematics of Data Science","issn_l":"2577-0187","issn":["2577-0187"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Mathematics of Data Science","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1804.05464","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.05464","pdf_url":"https://arxiv.org/pdf/1804.05464","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_type":"text"},{"id":"pmh:oai:authors.library.caltech.edu:110745","is_oa":false,"landing_page_url":"https://resolver.caltech.edu/CaltechAUTHORS:20210907-200115513","pdf_url":null,"source":{"id":"https://openalex.org/S4306402161","display_name":"CaltechAUTHORS (California Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122411786","host_organization_name":"California Institute of Technology","host_organization_lineage":["https://openalex.org/I122411786"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1137/18m1231298","is_oa":true,"landing_page_url":"https://doi.org/10.1137/18m1231298","pdf_url":"https://epubs.siam.org/doi/pdf/10.1137/18M1231298","source":{"id":"https://openalex.org/S4210229561","display_name":"SIAM Journal on Mathematics of Data Science","issn_l":"2577-0187","issn":["2577-0187"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Mathematics of Data Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4532442909","display_name":null,"funder_award_id":"FA8750-18-C-0101","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G6577325187","display_name":null,"funder_award_id":"CNS:1656873","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3006882295.pdf","grobid_xml":"https://content.openalex.org/works/W3006882295.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1967049706","https://openalex.org/W1967250398","https://openalex.org/W1968360652","https://openalex.org/W1972221945","https://openalex.org/W1993203591","https://openalex.org/W2015836240","https://openalex.org/W2019521193","https://openalex.org/W2105643086","https://openalex.org/W2111425084","https://openalex.org/W2145037371","https://openalex.org/W2551645646","https://openalex.org/W2783096200","https://openalex.org/W2963994557","https://openalex.org/W3022321359","https://openalex.org/W4212928962","https://openalex.org/W4230847851"],"related_works":[],"abstract_inverted_index":{"We":[0,60],"introduce":[1],"a":[2,11,40,56],"general":[3],"framework":[4],"for":[5,145],"competitive":[6,24],"gradient-based":[7,25,57],"learning":[8,16,26,58],"that":[9,48,134,149,154],"encompasses":[10],"wide":[12],"breadth":[13],"of":[14,23,43,67,93,99,105,121,138],"multiagent":[15,146],"algorithms,":[17],"and":[18,35,74,86,97],"analyze":[19],"the":[20,44,65,83,91,106,119,127,136],"limiting":[21],"behavior":[22],"algorithms":[27],"using":[28,110],"dynamical":[29],"systems":[30],"theory.":[31],"For":[32],"both":[33],"general-sum":[34],"potential":[36],"games,":[37,76],"we":[38,130],"characterize":[39],"nonnegligible":[41],"subset":[42],"local":[45],"Nash":[46,152],"equilibria":[47,153],"will":[49],"be":[50],"avoided":[51,158],"if":[52],"each":[53],"agent":[54],"employs":[55],"algorithm.":[59,94],"also":[61],"shed":[62],"light":[63],"on":[64],"issue":[66],"convergence":[68],"to":[69,82,90],"non-Nash":[70],"strategies":[71,101],"in":[72,113,118],"general-":[73],"zero-sum":[75,114],"which":[77],"may":[78,102],"have":[79],"no":[80],"relevance":[81],"underlying":[84],"game,":[85],"arise":[87],"solely":[88],"due":[89],"choice":[92],"The":[95],"existence":[96],"frequency":[98,137],"such":[100],"explain":[103],"some":[104],"difficulties":[107],"encountered":[108],"when":[109],"gradient":[111],"descent":[112],"games":[115,142],"as,":[116],"e.g.,":[117],"training":[120],"generative":[122],"adversarial":[123],"networks.":[124],"To":[125],"reinforce":[126],"theoretical":[128],"contributions,":[129],"provide":[131],"empirical":[132],"results":[133],"highlight":[135],"linear":[139],"quadratic":[140],"dynamic":[141],"(a":[143],"benchmark":[144],"reinforcement":[147],"learning)":[148],"admit":[150],"global":[151],"are":[155],"almost":[156],"surely":[157],"by":[159],"policy":[160],"gradient.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":3}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2020-03-06T00:00:00"}