{"id":"https://openalex.org/W361876","doi":null,"title":"Rational and convergent learning in stochastic games","display_name":"Rational and convergent learning in stochastic games","publication_year":2001,"publication_date":"2001-08-04","ids":{"openalex":"https://openalex.org/W361876","mag":"361876"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1.8663","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.8663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-2.cs.cmu.edu/~mmv/papers/01ijcai-mike.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"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":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Bowling","raw_affiliation_strings":["Computer Science Department, Carnegie-Mellon University, Pittsburgh, Pa"],"raw_orcid":"https://orcid.org/0000-0003-2960-8418","affiliations":[{"raw_affiliation_string":"Computer Science Department, Carnegie-Mellon University, Pittsburgh, Pa","institution_ids":["https://openalex.org/I74973139"]}]},{"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":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manuela Veloso","raw_affiliation_strings":["Computer Science Department, Carnegie-Mellon University, Pittsburgh, Pa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Carnegie-Mellon University, Pittsburgh, Pa","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":11.3579,"has_fulltext":false,"cited_by_count":285,"citation_normalized_percentile":{"value":0.98728709,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1021","last_page":"1026"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976000189781189,"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":0.9976000189781189,"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":0.0010000000474974513,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.0006000000284984708,"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/stochastic-games","display_name":"stochastic games","score":0.8429999947547913},{"id":"https://openalex.org/keywords/policy-learning","display_name":"policy learning","score":0.8080000281333923},{"id":"https://openalex.org/keywords/multi-agent-learning","display_name":"multi-agent learning","score":0.8259999752044678},{"id":"https://openalex.org/keywords/rational-learning","display_name":"rational learning","score":0.574999988079071},{"id":"https://openalex.org/keywords/convergence","display_name":"convergence","score":0.7570000290870667},{"id":"https://openalex.org/keywords/reinforcement-learning-algorithms","display_name":"reinforcement learning algorithms","score":0.8309999704360962},{"id":"https://openalex.org/keywords/adaptive-learning-rate","display_name":"adaptive learning rate","score":0.42399999499320984},{"id":"https://openalex.org/keywords/learning-agents","display_name":"learning agents","score":0.3179999887943268}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7920853495597839},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7403568029403687},{"id":"https://openalex.org/C2779913896","wikidata":"https://www.wikidata.org/wiki/Q7063001","display_name":"Notice","level":2,"score":0.710419774055481},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7099868059158325},{"id":"https://openalex.org/C201717286","wikidata":"https://www.wikidata.org/wiki/Q938185","display_name":"Rationality","level":2,"score":0.5352455377578735},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4979426860809326},{"id":"https://openalex.org/C58694771","wikidata":"https://www.wikidata.org/wiki/Q814385","display_name":"Bounded rationality","level":2,"score":0.49077877402305603},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4846530556678772},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4107092022895813},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3774765729904175},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1612166464328766},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.06896930932998657},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":5,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1.8663","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.8663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-2.cs.cmu.edu/~mmv/papers/01ijcai-mike.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.21.3510","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.21.3510","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/01ijcai.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.71.4834","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.71.4834","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/01ijcai.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.75.4898","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.75.4898","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.stanford.edu/class/cs224m/papers/bowling01rational.pdf","raw_type":"text"},{"id":"mag:361876","doi":null,"is_oa":false,"landing_page_url":"https://webdocs.cs.ualberta.ca/~bowling/papers/01ijcai-wolf.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","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 Joint Conference on Artificial Intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1513468570","https://openalex.org/W1515851193","https://openalex.org/W1530487017","https://openalex.org/W1542941925","https://openalex.org/W1607392272","https://openalex.org/W1907356258","https://openalex.org/W1967608200","https://openalex.org/W2011845369","https://openalex.org/W2067050450","https://openalex.org/W2104602264","https://openalex.org/W2147492008","https://openalex.org/W2150339816","https://openalex.org/W2160067530","https://openalex.org/W2164056559","https://openalex.org/W2575731723","https://openalex.org/W2797585760","https://openalex.org/W2911283634","https://openalex.org/W2914656440"],"related_works":["https://openalex.org/W7095987282","https://openalex.org/W7100479116","https://openalex.org/W202381653","https://openalex.org/W7097499919","https://openalex.org/W2120327309","https://openalex.org/W1812360833","https://openalex.org/W2364975238","https://openalex.org/W7208285799","https://openalex.org/W2135017242","https://openalex.org/W1515108343"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,12,32,106],"problem":[4],"of":[5,34,102],"policy":[6,71],"learning":[7,28,36,46,68],"in":[8,31],"multiagent":[9],"environments":[10],"using":[11],"stochastic":[13,103],"game":[14],"framework,":[15],"which":[16],"we":[17,95],"briefly":[18],"overview.":[19],"We":[20,42,63],"introduce":[21],"two":[22,51],"properties":[23,52],"as":[24],"desirable":[25],"for":[26,99],"a":[27,66,77,100],"agent":[29],"when":[30],"presence":[33],"other":[35],"agents,":[37],"namely":[38],"rationality":[39],"and":[40,53,94],"convergence.":[41],"examine":[43],"existing":[44],"reinforcement":[45],"algorithms":[47],"according":[48],"to":[49,58,91],"these":[50],"notice":[54],"that":[55,73],"they":[56],"fail":[57],"simultaneously":[59],"meet":[60],"both":[61],"criteria.":[62],"then":[64],"contribute":[65],"new":[67],"algorithm,":[69],"WoLF":[70],"hillclimbing,":[72],"is":[74,89],"based":[75],"on":[76],"simple":[78],"principle:":[79],"\"learn":[80],"quickly":[81],"while":[82,85],"losing,":[83],"slowly":[84],"winning.\"":[86],"The":[87],"algorithm":[88,107],"proven":[90],"be":[92],"rational":[93],"present":[96],"empirical":[97],"results":[98],"number":[101],"games":[104],"showing":[105],"converges.":[108],"1":[109]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":28},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":14}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}