{"id":"https://openalex.org/W1964886424","doi":"https://doi.org/10.1142/s0219525902000535","title":"REINFORCEMENT LEARNING IN MARKOVIAN EVOLUTIONARY GAMES","display_name":"REINFORCEMENT LEARNING IN MARKOVIAN EVOLUTIONARY GAMES","publication_year":2002,"publication_date":"2002-03-01","ids":{"openalex":"https://openalex.org/W1964886424","doi":"https://doi.org/10.1142/s0219525902000535","mag":"1964886424"},"language":"en","primary_location":{"id":"doi:10.1142/s0219525902000535","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219525902000535","pdf_url":null,"source":{"id":"https://openalex.org/S107361000","display_name":"Advances in Complex Systems","issn_l":"0219-5259","issn":["0219-5259","1793-6802","1793-9615","1793-9623"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Complex Systems","raw_type":"journal-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/A5018541798","display_name":"Vivek S. Borkar","orcid":"https://orcid.org/0000-0003-0756-5402"},"institutions":[{"id":"https://openalex.org/I11947397","display_name":"Tata Institute of Fundamental Research","ror":"https://ror.org/03ht1xw27","country_code":"IN","type":"education","lineage":["https://openalex.org/I11947397","https://openalex.org/I2799351866","https://openalex.org/I3149292468"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"V. S. BORKAR","raw_affiliation_strings":["School of Technology and Computer Science, Tata Institute of Fundamental Research, Homi Bhabha Road,  Mumbai 400005, India","School of Technology and Computer Science, Tata Institute of Fundamental Research, Homi Bhabha Road, Mumbai 400005, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Technology and Computer Science, Tata Institute of Fundamental Research, Homi Bhabha Road,  Mumbai 400005, India","institution_ids":["https://openalex.org/I11947397"]},{"raw_affiliation_string":"School of Technology and Computer Science, Tata Institute of Fundamental Research, Homi Bhabha Road, Mumbai 400005, India","institution_ids":["https://openalex.org/I11947397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5018541798"],"corresponding_institution_ids":["https://openalex.org/I11947397"],"apc_list":null,"apc_paid":null,"fwci":2.1318,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.88136267,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"05","issue":"01","first_page":"55","last_page":"72"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9961000084877014,"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":0.9961000084877014,"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":0.9746999740600586,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9718000292778015,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8032289743423462},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.6088832020759583},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5857760906219482},{"id":"https://openalex.org/keywords/evolutionary-game-theory","display_name":"Evolutionary game theory","score":0.5611262321472168},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5520480275154114},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.5180602073669434},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.4895671308040619},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47889652848243713},{"id":"https://openalex.org/keywords/replicator-equation","display_name":"Replicator equation","score":0.47484758496284485},{"id":"https://openalex.org/keywords/ordinary-differential-equation","display_name":"Ordinary differential equation","score":0.44005727767944336},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.39431485533714294},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.3782249391078949},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.35393026471138},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3520022928714752},{"id":"https://openalex.org/keywords/differential-equation","display_name":"Differential equation","score":0.28148317337036133},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2589775621891022}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8032289743423462},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.6088832020759583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5857760906219482},{"id":"https://openalex.org/C20249471","wikidata":"https://www.wikidata.org/wiki/Q2298789","display_name":"Evolutionary game theory","level":3,"score":0.5611262321472168},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5520480275154114},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.5180602073669434},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4895671308040619},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47889652848243713},{"id":"https://openalex.org/C50318809","wikidata":"https://www.wikidata.org/wiki/Q2145081","display_name":"Replicator equation","level":3,"score":0.47484758496284485},{"id":"https://openalex.org/C51544822","wikidata":"https://www.wikidata.org/wiki/Q465274","display_name":"Ordinary differential equation","level":3,"score":0.44005727767944336},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.39431485533714294},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.3782249391078949},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.35393026471138},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3520022928714752},{"id":"https://openalex.org/C78045399","wikidata":"https://www.wikidata.org/wiki/Q11214","display_name":"Differential equation","level":2,"score":0.28148317337036133},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2589775621891022},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1142/s0219525902000535","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219525902000535","pdf_url":null,"source":{"id":"https://openalex.org/S107361000","display_name":"Advances in Complex Systems","issn_l":"0219-5259","issn":["0219-5259","1793-6802","1793-9615","1793-9623"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Complex Systems","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:wsi:acsxxx:v:05:y:2002:i:01:n:s0219525902000535","is_oa":false,"landing_page_url":"http://www.worldscientific.com/doi/abs/10.1142/S0219525902000535","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:RePEc:wsi:acsxxx:v:05:y:2002:i:01:p:55-72","is_oa":false,"landing_page_url":"http://www.worldscinet.com/cgi-bin/details.cgi?type=html&id=pii:S0219525902000535","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320719","display_name":"Department of Science and Technology, Ministry of Science and Technology, India","ror":"https://ror.org/0101xrq71"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W361876","https://openalex.org/W1513468570","https://openalex.org/W1546006912","https://openalex.org/W1568229137","https://openalex.org/W1574700590","https://openalex.org/W1604363237","https://openalex.org/W1607392272","https://openalex.org/W1835254890","https://openalex.org/W1968970450","https://openalex.org/W1973039793","https://openalex.org/W1994616650","https://openalex.org/W1995622844","https://openalex.org/W2043224605","https://openalex.org/W2070214254","https://openalex.org/W2082261506","https://openalex.org/W2085728653","https://openalex.org/W2091565802","https://openalex.org/W2094364653","https://openalex.org/W2117138095","https://openalex.org/W2123597892","https://openalex.org/W2161061197","https://openalex.org/W2169225433","https://openalex.org/W2171234133","https://openalex.org/W2321878986","https://openalex.org/W2334782222","https://openalex.org/W2797585760","https://openalex.org/W2855817222","https://openalex.org/W2914656440","https://openalex.org/W3011120880"],"related_works":["https://openalex.org/W1593767881","https://openalex.org/W2360754740","https://openalex.org/W1615974028","https://openalex.org/W4297938064","https://openalex.org/W2384572063","https://openalex.org/W2407048069","https://openalex.org/W1605297503","https://openalex.org/W2005475838","https://openalex.org/W2145979805","https://openalex.org/W2505734641"],"abstract_inverted_index":{"A":[0,25],"population":[1],"of":[2,41,58,75,82],"agents":[3,45],"plays":[4],"a":[5,17],"stochastic":[6],"dynamic":[7],"game":[8],"wherein":[9],"there":[10],"is":[11,28,61],"an":[12,38,64],"underlying":[13],"state":[14],"process":[15,40],"with":[16],"Markovian":[18],"dynamics":[19],"that":[20],"also":[21],"affects":[22],"their":[23,51],"costs.":[24],"learning":[26,84],"mechanism":[27],"proposed":[29],"which":[30],"takes":[31],"into":[32],"account":[33],"intertemporal":[34],"effects":[35],"and":[36,72],"incorporates":[37],"explicit":[39],"expectation":[42],"formation.":[43],"The":[44,55],"use":[46],"this":[47,59],"scheme":[48,60,77],"to":[49],"update":[50],"mixed":[52],"strategies":[53],"incrementally.":[54],"asymptotic":[56],"behavior":[57],"captured":[62],"by":[63],"associated":[65],"ordinary":[66],"differential":[67],"equation.":[68],"Both":[69],"the":[70,73,76,80],"formulation":[71],"analysis":[74],"draw":[78],"upon":[79],"theory":[81],"reinforcement":[83],"in":[85],"artificial":[86],"intelligence.":[87]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}