{"id":"https://openalex.org/W4405464790","doi":"https://doi.org/10.1145/3670865.3673491","title":"Two-Timescale Q-Learning with Function Approximation in Zero-Sum Stochastic Games","display_name":"Two-Timescale Q-Learning with Function Approximation in Zero-Sum Stochastic Games","publication_year":2024,"publication_date":"2024-07-08","ids":{"openalex":"https://openalex.org/W4405464790","doi":"https://doi.org/10.1145/3670865.3673491"},"language":"en","primary_location":{"id":"doi:10.1145/3670865.3673491","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3670865.3673491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM Conference on Economics and Computation","raw_type":"proceedings-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/A5058269077","display_name":"Zaiwei Chen","orcid":"https://orcid.org/0000-0001-9915-5595"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zaiwei Chen","raw_affiliation_strings":["Computing + Mathematical Sciences, Caltech, Pasadena, CA, USA"],"affiliations":[{"raw_affiliation_string":"Computing + Mathematical Sciences, Caltech, Pasadena, CA, USA","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047410441","display_name":"Kaiqing Zhang","orcid":"https://orcid.org/0000-0002-7446-7581"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaiqing Zhang","raw_affiliation_strings":["Electrical and Computer Engineering, University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089549365","display_name":"Eric Mazumdar","orcid":"https://orcid.org/0000-0002-1815-269X"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Mazumdar","raw_affiliation_strings":["Computing + Mathematical Sciences, Caltech, Pasadena, CA, USA"],"affiliations":[{"raw_affiliation_string":"Computing + Mathematical Sciences, Caltech, Pasadena, CA, USA","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067307504","display_name":"Asuman Ozdaglar","orcid":"https://orcid.org/0000-0002-1827-1285"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Asuman Ozdaglar","raw_affiliation_strings":["Electrical Engineering and Computer Science, MIT, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science, MIT, Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062565732","display_name":"Adam Wierman","orcid":"https://orcid.org/0000-0002-5923-0199"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Wierman","raw_affiliation_strings":["Computing + Mathematical Sciences, Caltech, Pasadena, CA, United States"],"affiliations":[{"raw_affiliation_string":"Computing + Mathematical Sciences, Caltech, Pasadena, CA, United States","institution_ids":["https://openalex.org/I122411786"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5058269077"],"corresponding_institution_ids":["https://openalex.org/I122411786"],"apc_list":null,"apc_paid":null,"fwci":0.3617,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67191789,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"378","last_page":"378"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9624999761581421,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9624999761581421,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.951200008392334,"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/T12676","display_name":"Machine Learning and ELM","score":0.9380000233650208,"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/zero","display_name":"Zero (linguistics)","score":0.703933596611023},{"id":"https://openalex.org/keywords/zero-sum-game","display_name":"Zero-sum game","score":0.6453056335449219},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5432918667793274},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.4548022449016571},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.4504278600215912},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.43373903632164},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.42143112421035767},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3839758038520813},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.38221848011016846},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3733656406402588},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.29805684089660645},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.2532638907432556},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21481427550315857},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.20312818884849548},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.14435145258903503},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.05943748354911804}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.703933596611023},{"id":"https://openalex.org/C136356330","wikidata":"https://www.wikidata.org/wiki/Q156612","display_name":"Zero-sum game","level":3,"score":0.6453056335449219},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5432918667793274},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.4548022449016571},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.4504278600215912},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43373903632164},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.42143112421035767},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3839758038520813},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38221848011016846},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3733656406402588},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.29805684089660645},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.2532638907432556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21481427550315857},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.20312818884849548},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.14435145258903503},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.05943748354911804},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3670865.3673491","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3670865.3673491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM Conference on Economics and Computation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G137487548","display_name":null,"funder_award_id":"CPS-2136197","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3333941999","display_name":null,"funder_award_id":"Career Award 2240110","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8374379671","display_name":null,"funder_award_id":"CNS-2146814","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8523133835","display_name":null,"funder_award_id":"CNS-2106403","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8765427599","display_name":null,"funder_award_id":"NGSDI-2105648","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2739681863","https://openalex.org/W3170723600","https://openalex.org/W4287122294","https://openalex.org/W2039187327","https://openalex.org/W4307291161","https://openalex.org/W1877069894","https://openalex.org/W2979432606","https://openalex.org/W1994737592","https://openalex.org/W2123424061","https://openalex.org/W2151661095"],"abstract_inverted_index":{"We":[0],"consider":[1],"two-player":[2],"zero-sum":[3],"stochastic":[4,39],"games":[5],"and":[6,21,48,70],"propose":[7],"a":[8,44,63],"two-timescale":[9,28],"variant":[10,47],"of":[11,79,88,101],"Q-learning":[12],"with":[13],"function":[14,81],"approximation":[15],"that":[16],"is":[17],"payoff-based,":[18],"convergent,":[19],"rational,":[20],"symmetric":[22],"between":[23,66],"the":[24,30,38,49,57,71,76,86,91],"two":[25],"players.":[26],"In":[27,75],"Q-learning,":[29],"fast-timescale":[31,73],"iterates":[32,51],"are":[33,59],"updated":[34,60],"in":[35],"spirit":[36],"to":[37,55,85],"gradient":[40],"descent":[41],"for":[42,96],"minimizing":[43],"Bellman":[45],"error":[46],"slow-timescale":[50],"(which":[52],"we":[53,83],"use":[54],"compute":[56],"policies)":[58],"by":[61],"taking":[62],"convex":[64],"combination":[65],"its":[67],"previous":[68],"iterate":[69],"latest":[72],"iterate.":[74],"special":[77],"case":[78],"linear":[80],"approximation,":[82],"present,":[84],"best":[87],"our":[89],"knowledge,":[90],"first":[92],"last-iterate":[93],"finite-sample":[94],"bound":[95],"payoff-based":[97],"independent":[98],"learning":[99],"dynamics":[100],"these":[102],"types.":[103]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}