{"id":"https://openalex.org/W2169383220","doi":"https://doi.org/10.1109/adprl.2009.4927546","title":"Multiagent reinforcement learning in extensive form games with complete information","display_name":"Multiagent reinforcement learning in extensive form games with complete information","publication_year":2009,"publication_date":"2009-03-01","ids":{"openalex":"https://openalex.org/W2169383220","doi":"https://doi.org/10.1109/adprl.2009.4927546","mag":"2169383220"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2009.4927546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2009.4927546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning","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/A5110248946","display_name":"Ali Akramizadeh","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ali Akramizadeh","raw_affiliation_strings":["Center of Computational Intelligence and Large Scale System, EE Department, Polytechnic University, Iran"],"affiliations":[{"raw_affiliation_string":"Center of Computational Intelligence and Large Scale System, EE Department, Polytechnic University, Iran","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051122758","display_name":"Mohammad Bagher Menhaj","orcid":"https://orcid.org/0000-0002-9470-5532"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammad -B. Menhaj","raw_affiliation_strings":["Center of Computational Intelligence and Large Scale System, EE Department, Polytechnic University, Iran"],"affiliations":[{"raw_affiliation_string":"Center of Computational Intelligence and Large Scale System, EE Department, Polytechnic University, Iran","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015789245","display_name":"Ahmad Afshar","orcid":"https://orcid.org/0000-0002-9963-733X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmad Afshar","raw_affiliation_strings":["Center of Computational Intelligence and Large Scale System, EE Department, Polytechnic University, Iran"],"affiliations":[{"raw_affiliation_string":"Center of Computational Intelligence and Large Scale System, EE Department, Polytechnic University, Iran","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5110248946"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7447,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.87995663,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"205","last_page":"211"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9955000281333923,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9915000200271606,"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":0.8233003616333008},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6995441317558289},{"id":"https://openalex.org/keywords/subgame-perfect-equilibrium","display_name":"Subgame perfect equilibrium","score":0.6975753307342529},{"id":"https://openalex.org/keywords/extensive-form-game","display_name":"Extensive-form game","score":0.6835733652114868},{"id":"https://openalex.org/keywords/associative-property","display_name":"Associative property","score":0.6778460741043091},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5524317026138306},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5365661978721619},{"id":"https://openalex.org/keywords/subgame","display_name":"Subgame","score":0.49355947971343994},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.44442489743232727},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43012702465057373},{"id":"https://openalex.org/keywords/sequential-game","display_name":"Sequential game","score":0.3858911991119385},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.3781639337539673},{"id":"https://openalex.org/keywords/equilibrium-selection","display_name":"Equilibrium selection","score":0.374135285615921},{"id":"https://openalex.org/keywords/repeated-game","display_name":"Repeated game","score":0.36950236558914185},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.3665146827697754},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21722561120986938}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8233003616333008},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6995441317558289},{"id":"https://openalex.org/C175983524","wikidata":"https://www.wikidata.org/wiki/Q1615834","display_name":"Subgame perfect equilibrium","level":3,"score":0.6975753307342529},{"id":"https://openalex.org/C146930158","wikidata":"https://www.wikidata.org/wiki/Q656416","display_name":"Extensive-form game","level":4,"score":0.6835733652114868},{"id":"https://openalex.org/C159423971","wikidata":"https://www.wikidata.org/wiki/Q177251","display_name":"Associative property","level":2,"score":0.6778460741043091},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5524317026138306},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5365661978721619},{"id":"https://openalex.org/C13576547","wikidata":"https://www.wikidata.org/wiki/Q3965283","display_name":"Subgame","level":5,"score":0.49355947971343994},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.44442489743232727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43012702465057373},{"id":"https://openalex.org/C73795354","wikidata":"https://www.wikidata.org/wiki/Q287618","display_name":"Sequential game","level":3,"score":0.3858911991119385},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.3781639337539673},{"id":"https://openalex.org/C164407509","wikidata":"https://www.wikidata.org/wiki/Q5384490","display_name":"Equilibrium selection","level":4,"score":0.374135285615921},{"id":"https://openalex.org/C202556891","wikidata":"https://www.wikidata.org/wiki/Q1584646","display_name":"Repeated game","level":3,"score":0.36950236558914185},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.3665146827697754},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21722561120986938},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/adprl.2009.4927546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2009.4927546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W324981204","https://openalex.org/W1502765764","https://openalex.org/W1513468570","https://openalex.org/W1515891729","https://openalex.org/W1564534945","https://openalex.org/W1606998818","https://openalex.org/W1689629105","https://openalex.org/W2099618002","https://openalex.org/W2109910161","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2122410182","https://openalex.org/W2140790422","https://openalex.org/W2145067550","https://openalex.org/W2147492008","https://openalex.org/W2169747811","https://openalex.org/W2623293810","https://openalex.org/W2782037066","https://openalex.org/W4214717370","https://openalex.org/W6611181476","https://openalex.org/W6630520071","https://openalex.org/W6681342480"],"related_works":["https://openalex.org/W3121536674","https://openalex.org/W2000358093","https://openalex.org/W2025486390","https://openalex.org/W3123151717","https://openalex.org/W2892045649","https://openalex.org/W2951958824","https://openalex.org/W3035137804","https://openalex.org/W2387562499","https://openalex.org/W4248854763","https://openalex.org/W2382996178"],"abstract_inverted_index":{"Recent":[0],"developments":[1],"in":[2,26,36,54,68,86],"multiagent":[3],"reinforcement":[4],"learning,":[5],"mostly":[6],"concentrate":[7],"on":[8],"normal":[9],"form":[10,15,28],"games":[11,29],"or":[12],"restrictive":[13],"hierarchical":[14],"games.":[16],"In":[17],"this":[18],"paper,":[19],"we":[20],"use":[21],"the":[22,80,95,98],"well":[23],"known":[24],"Q-learning":[25],"extensive":[27],"which":[30,48,71,90],"agents":[31],"have":[32],"a":[33,42,59,87],"fixed":[34],"priority":[35],"action":[37,55],"selection.":[38],"We":[39],"also":[40,64],"introduce":[41],"new":[43],"concept":[44],"called":[45],"associative":[46],"Q-values":[47,78],"not":[49],"only":[50],"can":[51,65],"be":[52,66,75],"used":[53,67],"selection,":[56],"leading":[57],"to":[58,74],"subgame":[60,99],"perfect":[61,100],"equilibrium,":[62],"but":[63],"update":[69],"rule":[70],"is":[72,91],"proved":[73],"convergent.":[76],"Associative":[77],"are":[79],"expected":[81],"utility":[82],"of":[83,94,97],"an":[84,92],"agent":[85],"game":[88],"situation":[89],"estimate":[93],"value":[96],"equilibrium":[101],"point.":[102]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}