{"id":"https://openalex.org/W2168517872","doi":"https://doi.org/10.1145/1329125.1329173","title":"Theoretical advantages of lenient Q-learners","display_name":"Theoretical advantages of lenient Q-learners","publication_year":2007,"publication_date":"2007-05-14","ids":{"openalex":"https://openalex.org/W2168517872","doi":"https://doi.org/10.1145/1329125.1329173","mag":"2168517872"},"language":"en","primary_location":{"id":"doi:10.1145/1329125.1329173","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1329125.1329173","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems","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/A5008038676","display_name":"Liviu Panait","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Liviu Panait","raw_affiliation_strings":["Google Inc, Santa Monica, CA"],"affiliations":[{"raw_affiliation_string":"Google Inc, Santa Monica, CA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008547992","display_name":"Karl Tuyls","orcid":"https://orcid.org/0000-0001-7929-1944"},"institutions":[{"id":"https://openalex.org/I34352273","display_name":"Maastricht University","ror":"https://ror.org/02jz4aj89","country_code":"NL","type":"education","lineage":["https://openalex.org/I34352273"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Karl Tuyls","raw_affiliation_strings":["Maastricht University, MiCC-IKAT, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Maastricht University, MiCC-IKAT, The Netherlands","institution_ids":["https://openalex.org/I34352273"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5008038676"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.408,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.862176,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9972000122070312,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9972000122070312,"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/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.9968000054359436,"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/replicator-equation","display_name":"Replicator equation","score":0.8278553485870361},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8098452687263489},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7633137702941895},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7035393118858337},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6994625329971313},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5452176332473755},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5429894328117371},{"id":"https://openalex.org/keywords/differential","display_name":"Differential (mechanical device)","score":0.44803664088249207},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3521685004234314},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3240225315093994},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1859627664089203},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09640684723854065}],"concepts":[{"id":"https://openalex.org/C50318809","wikidata":"https://www.wikidata.org/wiki/Q2145081","display_name":"Replicator equation","level":3,"score":0.8278553485870361},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8098452687263489},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7633137702941895},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7035393118858337},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6994625329971313},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5452176332473755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5429894328117371},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.44803664088249207},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3521685004234314},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3240225315093994},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1859627664089203},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09640684723854065},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1329125.1329173","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1329125.1329173","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems","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":48,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W95848126","https://openalex.org/W137071854","https://openalex.org/W176190316","https://openalex.org/W177097005","https://openalex.org/W1415442047","https://openalex.org/W1495235237","https://openalex.org/W1505866611","https://openalex.org/W1512089703","https://openalex.org/W1515851193","https://openalex.org/W1546006912","https://openalex.org/W1551880564","https://openalex.org/W1555689267","https://openalex.org/W1560074431","https://openalex.org/W1607392272","https://openalex.org/W1805994660","https://openalex.org/W1960351623","https://openalex.org/W1963754118","https://openalex.org/W1967829443","https://openalex.org/W2015071010","https://openalex.org/W2021958841","https://openalex.org/W2031098375","https://openalex.org/W2042521440","https://openalex.org/W2070898118","https://openalex.org/W2085366587","https://openalex.org/W2085728653","https://openalex.org/W2100211715","https://openalex.org/W2104602264","https://openalex.org/W2107544712","https://openalex.org/W2117359632","https://openalex.org/W2119396705","https://openalex.org/W2121863487","https://openalex.org/W2129936995","https://openalex.org/W2144357723","https://openalex.org/W2152828142","https://openalex.org/W2164197363","https://openalex.org/W2312609093","https://openalex.org/W2408428930","https://openalex.org/W2797585760","https://openalex.org/W2906795987","https://openalex.org/W2913602408","https://openalex.org/W3121365957","https://openalex.org/W3122924345","https://openalex.org/W4214717370","https://openalex.org/W6677916085","https://openalex.org/W7047599447","https://openalex.org/W7065811666","https://openalex.org/W7075337242"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,59,87,99,108],"dynamics":[4],"of":[5,43,61,63,89,96,110],"multiple":[6],"reinforcement":[7,117],"learning":[8],"agents":[9,38],"from":[10],"an":[11],"Evolutionary":[12],"Game":[13],"Theoretic":[14],"(EGT)":[15],"perspective.":[16],"We":[17,51],"provide":[18],"a":[19,113],"Replicator":[20],"Dynamics":[21],"model":[22,56],"for":[23,35,86,115],"traditional":[24,65],"multiagent":[25,68,116],"Q-learning,":[26],"and":[27,66],"we":[28],"extend":[29],"these":[30],"differential":[31],"equations":[32],"to":[33,57,98],"account":[34],"lenient":[36,67],"learners:":[37],"that":[39,46,78],"forgive":[40],"possible":[41],"mistakes":[42],"their":[44,90],"teammates":[45],"resulted":[47],"in":[48,70,93],"lower":[49],"rewards.":[50],"use":[52],"this":[53],"extended":[54],"formal":[55],"visualize":[58],"basins":[60],"attraction":[62],"both":[64],"Q-learners":[69],"two":[71],"benchmark":[72],"coordination":[73],"problems.":[74],"The":[75],"results":[76],"indicate":[77],"lenience":[79],"provides":[80],"learners":[81],"with":[82],"more":[83],"accurate":[84],"estimates":[85],"utility":[88],"actions,":[91],"resulting":[92],"higher":[94],"likelihood":[95],"convergence":[97],"globally":[100],"optimal":[101],"solution.":[102],"In":[103],"addition,":[104],"our":[105],"research":[106],"supports":[107],"strength":[109],"EGT":[111],"as":[112],"backbone":[114],"learning.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}