{"id":"https://openalex.org/W2152711271","doi":"https://doi.org/10.1109/acc.2011.5990832","title":"Decentralized learning in two-player zero-sum games: A L<inf>R-I</inf> lagging anchor algorithm","display_name":"Decentralized learning in two-player zero-sum games: A L<inf>R-I</inf> lagging anchor algorithm","publication_year":2011,"publication_date":"2011-06-01","ids":{"openalex":"https://openalex.org/W2152711271","doi":"https://doi.org/10.1109/acc.2011.5990832","mag":"2152711271"},"language":"en","primary_location":{"id":"doi:10.1109/acc.2011.5990832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2011.5990832","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 American Control Conference","raw_type":"proceedings-article"},"type":"conference-paper","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/A5000784485","display_name":"Xiaosong Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I67031392","display_name":"Carleton University","ror":"https://ror.org/02qtvee93","country_code":"CA","type":"education","lineage":["https://openalex.org/I67031392"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xiaosong Lu","raw_affiliation_strings":["Department of Systems and Computer Engineering, Carleton University, Ottawa, ONT, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems and Computer Engineering, Carleton University, Ottawa, ONT, Canada","institution_ids":["https://openalex.org/I67031392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018347314","display_name":"Howard M. Schwartz","orcid":"https://orcid.org/0000-0002-4489-5892"},"institutions":[{"id":"https://openalex.org/I67031392","display_name":"Carleton University","ror":"https://ror.org/02qtvee93","country_code":"CA","type":"education","lineage":["https://openalex.org/I67031392"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Howard M. Schwartz","raw_affiliation_strings":["Department of Systems and Computer Engineering, Carleton University, Ottawa, ONT, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems and Computer Engineering, Carleton University, Ottawa, ONT, Canada","institution_ids":["https://openalex.org/I67031392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I67031392"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.21682671,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"49","issue":null,"first_page":"107","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9976999759674072,"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":0.9961000084877014,"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/lagging","display_name":"Lagging","score":0.8895360231399536},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6643210649490356},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5381046533584595},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.49701860547065735},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48635607957839966},{"id":"https://openalex.org/keywords/zero-sum-game","display_name":"Zero-sum game","score":0.4433116316795349},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.43048518896102905},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.43030211329460144},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42663463950157166},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3892495036125183},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.3486865162849426},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2807103395462036},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1209191381931305},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08902809023857117},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.0618324875831604}],"concepts":[{"id":"https://openalex.org/C2776962539","wikidata":"https://www.wikidata.org/wiki/Q6472078","display_name":"Lagging","level":2,"score":0.8895360231399536},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6643210649490356},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5381046533584595},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.49701860547065735},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48635607957839966},{"id":"https://openalex.org/C136356330","wikidata":"https://www.wikidata.org/wiki/Q156612","display_name":"Zero-sum game","level":3,"score":0.4433116316795349},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.43048518896102905},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.43030211329460144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42663463950157166},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3892495036125183},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.3486865162849426},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2807103395462036},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1209191381931305},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08902809023857117},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0618324875831604},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acc.2011.5990832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2011.5990832","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 American Control Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1569077671","https://openalex.org/W1574638321","https://openalex.org/W1602326725","https://openalex.org/W1607392272","https://openalex.org/W1689629105","https://openalex.org/W1986043874","https://openalex.org/W2090697311","https://openalex.org/W2099618002","https://openalex.org/W2120327309","https://openalex.org/W2147492008","https://openalex.org/W2169194711","https://openalex.org/W2484003876","https://openalex.org/W6636288269"],"related_works":["https://openalex.org/W2739681863","https://openalex.org/W3170723600","https://openalex.org/W4287122294","https://openalex.org/W2039187327","https://openalex.org/W3011680666","https://openalex.org/W3136378956","https://openalex.org/W4287871712","https://openalex.org/W3006995042","https://openalex.org/W3004964213","https://openalex.org/W2885522335"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,9,28],"LR-Ilagging":[4],"anchor":[5,11],"algorithm":[6,23],"that":[7,19],"combines":[8],"lagging":[10],"method":[12],"to":[13,27],"the":[14],"LR-Ilearning":[15],"algorithm.":[16],"We":[17],"prove":[18],"this":[20],"decentralized":[21],"learning":[22],"converges":[24],"in":[25,31],"strategies":[26],"Nash":[29],"equilibrium":[30],"two-player,":[32],"zero-sum,":[33],"two-action":[34],"matrix":[35],"games,":[36],"while":[37],"only":[38],"needing":[39],"knowledge":[40],"of":[41],"their":[42],"own":[43],"action":[44],"and":[45],"reward.":[46]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}