{"id":"https://openalex.org/W1530487017","doi":null,"title":"Convergence of Gradient Dynamics with a Variable Learning Rate","display_name":"Convergence of Gradient Dynamics with a Variable Learning Rate","publication_year":2001,"publication_date":"2001-06-28","ids":{"openalex":"https://openalex.org/W1530487017","mag":"1530487017"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.21.5517","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.21.5517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~mhb/papers/01icml.ps.gz","raw_type":"text"},"volume":null,"type":"article","indexed_in":[],"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/A5081163135","display_name":"Michael Bowling","orcid":"https://orcid.org/0000-0003-2960-8418","observed_orcids":["https://orcid.org/0000-0003-2960-8418"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Bowling","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-2960-8418","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5088276691","display_name":"Manuela Veloso","orcid":"https://orcid.org/0000-0001-6738-238X","observed_orcids":["https://orcid.org/0000-0001-6738-238X","https://orcid.org/0000-0001-5355-1912"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manuela Veloso","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5126,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.93752596,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"27","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.8759999871253967,"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":0.8759999871253967,"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":0.09139999747276306,"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":0.01080000028014183,"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/gradient-ascent","display_name":"gradient ascent","score":0.7129999995231628},{"id":"https://openalex.org/keywords/variable-learning-rate","display_name":"variable learning rate","score":0.9610000252723694},{"id":"https://openalex.org/keywords/multi-agent-learning","display_name":"multi-agent learning","score":0.6930000185966492},{"id":"https://openalex.org/keywords/nash-equilibrium-convergence","display_name":"Nash equilibrium convergence","score":0.8519999980926514},{"id":"https://openalex.org/keywords/strategy-convergence","display_name":"strategy convergence","score":0.8209999799728394}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.648870587348938},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.5613444447517395},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.5361352562904358},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5160817503929138},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.45880475640296936},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32330435514450073},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2525370717048645},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11888954043388367},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10101154446601868},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.09256589412689209},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.09233853220939636},{"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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.21.5517","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.21.5517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~mhb/papers/01icml.ps.gz","raw_type":"text"},{"id":"mag:1530487017","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/icml/icml2001.html#BowlingV01","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W361876","https://openalex.org/W1518187106","https://openalex.org/W1605188341","https://openalex.org/W1607392272","https://openalex.org/W1994851329","https://openalex.org/W2011845369","https://openalex.org/W2109100253","https://openalex.org/W2109223704","https://openalex.org/W2149254401","https://openalex.org/W2797585760"],"related_works":["https://openalex.org/W2964419277","https://openalex.org/W1607392272","https://openalex.org/W2964220070","https://openalex.org/W2947252582","https://openalex.org/W3203238138","https://openalex.org/W70059180","https://openalex.org/W2120327309","https://openalex.org/W1504193820","https://openalex.org/W2893314716","https://openalex.org/W4386794468"],"abstract_inverted_index":{"As":[0],"multiagent":[1],"environments":[2],"become":[3],"more":[4],"prevalent":[5],"we":[6,115],"need":[7],"to":[8,110,144,159],"understand":[9],"how":[10],"this":[11,81,113,142],"changes":[12],"the":[13,23,48,83,92,100,126,135,148],"agent-based":[14],"paradigm.":[15],"One":[16],"aspect":[17],"that":[18,78,98,141,153],"is":[19,28,56],"heavily":[20],"affected":[21],"by":[22],"presence":[24],"of":[25,50,72,85,151],"multiple":[26],"agents":[27],"learning.":[29],"Traditional":[30],"learning":[31,51,119,136],"algorithms":[32,52],"have":[33],"core":[34],"assumptions,":[35],"such":[36],"as":[37],"Markovian":[38],"transitions,":[39],"which":[40],"are":[41,108],"violated":[42],"in":[43,53],"these":[44,54],"environments.":[45],"Yet,":[46],"understanding":[47],"behavior":[49],"domains":[55],"critical.":[57],"Singh,":[58],"Kearns,":[59],"and":[60,156],"Mansour":[61],"(2000)":[62],"examine":[63],"gradient":[64,122,145],"ascent":[65,146],"learning,":[66],"specifically":[67],"within":[68],"a":[69,117,160],"restricted":[70],"class":[71],"repeated":[73],"matrix":[74],"games.":[75],"They":[76],"prove":[77,140],"when":[79],"using":[80],"technique":[82],"average":[84],"expected":[86,105],"payoffs":[87,106,157],"over":[88],"time":[89],"converges.":[90],"On":[91],"other":[93],"hand,":[94],"they":[95],"also":[96],"show":[97],"neither":[99],"players'":[101],"strategies":[102,155],"nor":[103],"their":[104],"themselves":[107],"guaranteed":[109],"converge.":[111],"In":[112],"paper":[114],"introduce":[116],"variable":[118],"rate":[120],"for":[121,133],"ascent,":[123],"along":[124],"with":[125],"WoLF":[127],"(\"Win":[128],"or":[129],"Learn":[130],"Fast\")":[131],"principle":[132],"regulating":[134],"rate.":[137],"We":[138],"then":[139],"modification":[143],"has":[147],"stronger":[149],"notion":[150],"convergence,":[152],"is,":[154],"converge":[158],"Nash":[161],"equilibrium.":[162],"1.":[163]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}