{"id":"https://openalex.org/W2126421963","doi":"https://doi.org/10.1145/1329125.1329180","title":"Reinforcement learning in extensive form games with incomplete information","display_name":"Reinforcement learning in extensive form games with incomplete information","publication_year":2007,"publication_date":"2007-05-14","ids":{"openalex":"https://openalex.org/W2126421963","doi":"https://doi.org/10.1145/1329125.1329180","mag":"2126421963"},"language":"en","primary_location":{"id":"doi:10.1145/1329125.1329180","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1329125.1329180","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/A5014791481","display_name":"Alessandro Lazaric","orcid":"https://orcid.org/0000-0002-8970-413X"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Lazaric","raw_affiliation_strings":["Politecnico di Milano, Milan, Italy","Politecnico di Milano, Milan (Italy)#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Politecnico di Milano, Milan (Italy)#TAB#","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064277708","display_name":"Enrique Mu\u00f1oz de Cote","orcid":"https://orcid.org/0000-0002-3249-096X"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Enrique Munoz de Cote","raw_affiliation_strings":["Politecnico di Milano, Milan, Italy","Politecnico di Milano, Milan (Italy)#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Politecnico di Milano, Milan (Italy)#TAB#","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060367013","display_name":"Nicola Gatti","orcid":"https://orcid.org/0000-0001-7349-3932"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicola Gatti","raw_affiliation_strings":["Politecnico di Milano, Milan, Italy","Politecnico di Milano, Milan (Italy)#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Politecnico di Milano, Milan (Italy)#TAB#","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2909,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.93929766,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10991","display_name":"Game Theory and Voting Systems","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10991","display_name":"Game Theory and Voting Systems","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.9991999864578247,"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/T11182","display_name":"Auction Theory and Applications","score":0.9952999949455261,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7623960971832275},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6830679774284363},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4966884255409241},{"id":"https://openalex.org/keywords/complete-information","display_name":"Complete information","score":0.4674345552921295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39901071786880493},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.17392948269844055},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14207929372787476},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07096388936042786},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.054955095052719116}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7623960971832275},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6830679774284363},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4966884255409241},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.4674345552921295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39901071786880493},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.17392948269844055},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14207929372787476},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07096388936042786},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.054955095052719116}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1329125.1329180","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1329125.1329180","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":14,"referenced_works":["https://openalex.org/W1513468570","https://openalex.org/W1519783625","https://openalex.org/W1542941925","https://openalex.org/W1604616925","https://openalex.org/W2009736032","https://openalex.org/W2055890485","https://openalex.org/W2102690504","https://openalex.org/W2103138133","https://openalex.org/W2105440797","https://openalex.org/W2110667918","https://openalex.org/W2112374372","https://openalex.org/W2117357850","https://openalex.org/W2120327309","https://openalex.org/W2164637474"],"related_works":["https://openalex.org/W4210912933","https://openalex.org/W1562959674","https://openalex.org/W2923653485","https://openalex.org/W2957776456","https://openalex.org/W4224287422","https://openalex.org/W2952472710","https://openalex.org/W4255994452","https://openalex.org/W4206669594","https://openalex.org/W3005560120","https://openalex.org/W3037422413"],"abstract_inverted_index":{"We":[0,61],"consider":[1],"the":[2,31,51,56],"problem":[3],"of":[4,58],"playing":[5],"in":[6,50,65],"repeated":[7],"extensive":[8],"form":[9],"games":[10],"where":[11],"agents":[12],"do":[13],"not":[14],"have":[15],"any":[16],"prior.":[17],"In":[18,36],"this":[19,37,75],"situation":[20],"classic":[21],"game":[22],"theoretical":[23],"tools":[24],"are":[25],"inapplicable":[26],"and":[27,67],"it":[28,71],"is":[29],"common":[30],"resort":[32],"to":[33],"learning":[34,43,78],"techniques.":[35],"paper,":[38],"we":[39,68],"present":[40],"a":[41],"novel":[42],"principle":[44,76],"that":[45,73],"aims":[46],"at":[47],"avoiding":[48],"oscillations":[49],"agents'":[52],"strategies":[53],"induced":[54],"by":[55],"presence":[57],"concurrent":[59],"learners.":[60],"apply":[62],"our":[63],"algorithm":[64],"bargaining,":[66],"experimentally":[69],"evaluate":[70],"showing":[72],"using":[74],"reinforcement":[77],"algorithms":[79],"can":[80],"improve":[81],"their":[82],"convergence":[83],"time.":[84]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}