{"id":"https://openalex.org/W39810663","doi":"https://doi.org/10.3233/ida-2011-0502","title":"Exploration strategies in n-Person general-sum multiagent reinforcement learning with sequential action selection","display_name":"Exploration strategies in n-Person general-sum multiagent reinforcement learning with sequential action selection","publication_year":2011,"publication_date":"2011-11-08","ids":{"openalex":"https://openalex.org/W39810663","doi":"https://doi.org/10.3233/ida-2011-0502","mag":"39810663"},"language":"en","primary_location":{"id":"doi:10.3233/ida-2011-0502","is_oa":false,"landing_page_url":"https://doi.org/10.3233/ida-2011-0502","pdf_url":null,"source":{"id":"https://openalex.org/S2498839158","display_name":"Intelligent Data Analysis","issn_l":"1088-467X","issn":["1088-467X","1571-4128"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligent Data Analysis","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/A5110248946","display_name":"Ali Akramizadeh","orcid":null},"institutions":[{"id":"https://openalex.org/I158248296","display_name":"Amirkabir University of Technology","ror":"https://ror.org/04gzbav43","country_code":"IR","type":"education","lineage":["https://openalex.org/I158248296"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Ali Akramizadeh","raw_affiliation_strings":["Department of Electrical Engineering, Amir Kabir University of Technology, Tehran, Iran","[Department of Electrical Engineering, Amir kabir University of Technology, Tehran, Iran]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Amir Kabir University of Technology, Tehran, Iran","institution_ids":["https://openalex.org/I158248296"]},{"raw_affiliation_string":"[Department of Electrical Engineering, Amir kabir University of Technology, Tehran, Iran]","institution_ids":["https://openalex.org/I158248296"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015789245","display_name":"Ahmad Afshar","orcid":"https://orcid.org/0000-0002-9963-733X"},"institutions":[{"id":"https://openalex.org/I158248296","display_name":"Amirkabir University of Technology","ror":"https://ror.org/04gzbav43","country_code":"IR","type":"education","lineage":["https://openalex.org/I158248296"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Ahmad Afshar","raw_affiliation_strings":["Department of Electrical Engineering, Amir Kabir University of Technology, Tehran, Iran","[Department of Electrical Engineering, Amir kabir University of Technology, Tehran, Iran]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Amir Kabir University of Technology, Tehran, Iran","institution_ids":["https://openalex.org/I158248296"]},{"raw_affiliation_string":"[Department of Electrical Engineering, Amir kabir University of Technology, Tehran, Iran]","institution_ids":["https://openalex.org/I158248296"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051122758","display_name":"Mohammad Bagher Menhaj","orcid":"https://orcid.org/0000-0002-9470-5532"},"institutions":[{"id":"https://openalex.org/I158248296","display_name":"Amirkabir University of Technology","ror":"https://ror.org/04gzbav43","country_code":"IR","type":"education","lineage":["https://openalex.org/I158248296"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Mohammad B. Menhaj","raw_affiliation_strings":["Department of Electrical Engineering, Amir Kabir University of Technology, Tehran, Iran","[Department of Electrical Engineering, Amir kabir University of Technology, Tehran, Iran]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Amir Kabir University of Technology, Tehran, Iran","institution_ids":["https://openalex.org/I158248296"]},{"raw_affiliation_string":"[Department of Electrical Engineering, Amir kabir University of Technology, Tehran, Iran]","institution_ids":["https://openalex.org/I158248296"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5110248946"],"corresponding_institution_ids":["https://openalex.org/I158248296"],"apc_list":{"value":4150,"currency":"USD","value_usd":4150},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00358317,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":"6","first_page":"913","last_page":"929"},"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9908999800682068,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8448003530502319},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7387640476226807},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.7108019590377808},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.6661776304244995},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6148242950439453},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5908248424530029},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5715024471282959},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5549317002296448},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5547065138816833},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5435149669647217},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.524848461151123},{"id":"https://openalex.org/keywords/extensive-form-game","display_name":"Extensive-form game","score":0.4384104311466217},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.43006014823913574},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4123998284339905},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3454338312149048},{"id":"https://openalex.org/keywords/sequential-game","display_name":"Sequential game","score":0.3178812563419342},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2880515456199646},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.28225088119506836},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.17219412326812744},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15418386459350586}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8448003530502319},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7387640476226807},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.7108019590377808},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.6661776304244995},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6148242950439453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5908248424530029},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5715024471282959},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5549317002296448},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5547065138816833},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5435149669647217},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.524848461151123},{"id":"https://openalex.org/C146930158","wikidata":"https://www.wikidata.org/wiki/Q656416","display_name":"Extensive-form game","level":4,"score":0.4384104311466217},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.43006014823913574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4123998284339905},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3454338312149048},{"id":"https://openalex.org/C73795354","wikidata":"https://www.wikidata.org/wiki/Q287618","display_name":"Sequential game","level":3,"score":0.3178812563419342},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2880515456199646},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.28225088119506836},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.17219412326812744},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15418386459350586},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/ida-2011-0502","is_oa":false,"landing_page_url":"https://doi.org/10.3233/ida-2011-0502","pdf_url":null,"source":{"id":"https://openalex.org/S2498839158","display_name":"Intelligent Data Analysis","issn_l":"1088-467X","issn":["1088-467X","1571-4128"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligent Data Analysis","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1513468570","https://openalex.org/W1515851193","https://openalex.org/W1515891729","https://openalex.org/W1519783625","https://openalex.org/W1555689267","https://openalex.org/W1560074431","https://openalex.org/W1599398667","https://openalex.org/W1605188341","https://openalex.org/W1641379095","https://openalex.org/W1689629105","https://openalex.org/W2011528476","https://openalex.org/W2035681301","https://openalex.org/W2074457245","https://openalex.org/W2085366587","https://openalex.org/W2089649903","https://openalex.org/W2099618002","https://openalex.org/W2104602264","https://openalex.org/W2107544712","https://openalex.org/W2119120935","https://openalex.org/W2120846115","https://openalex.org/W2121863487","https://openalex.org/W2128643385","https://openalex.org/W2131967794","https://openalex.org/W2145067550","https://openalex.org/W2145279027","https://openalex.org/W2169383220","https://openalex.org/W2169747811","https://openalex.org/W3011120880","https://openalex.org/W3123022539"],"related_works":["https://openalex.org/W2808418668","https://openalex.org/W2357975469","https://openalex.org/W2101748387","https://openalex.org/W4380550992","https://openalex.org/W4322760752","https://openalex.org/W3096874164","https://openalex.org/W2970347269","https://openalex.org/W2146763310","https://openalex.org/W3167472281","https://openalex.org/W2937181779"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"two":[3,128],"novel":[4],"exploration":[5,81],"strategies":[6,82],"are":[7,84],"proposed":[8,80],"for":[9,45,120],"n-person":[10],"general-sum":[11],"multiagent":[12,123],"reinforcement":[13],"learning":[14,21,91],"with":[15,37,50,125],"sequential":[16,110],"action":[17,111],"selection.":[18],"The":[19],"existing":[20,97],"process,":[22],"called":[23,58],"extensive":[24,34],"Markov":[25],"game,":[26],"is":[27,57,106],"considered":[28],"as":[29],"a":[30],"set":[31],"of":[32,78,96,99],"successive":[33],"form":[35],"games":[36,49],"perfect":[38],"information.":[39],"We":[40],"introduce":[41],"an":[42],"estimated":[43],"value":[44],"taking":[46],"actions":[47,67],"in":[48,86],"respect":[51],"to":[52,65,70,108],"other":[53],"agents'":[54],"preferences":[55],"which":[56],"associative":[59],"Q-value.":[60],"They":[61],"can":[62],"be":[63,117],"used":[64,85],"select":[66],"probabilistically":[68],"according":[69],"Boltzmann":[71],"distribution.":[72],"Simulation":[73],"results":[74],"present":[75],"the":[76,79,94],"effectiveness":[77],"that":[83],"our":[87],"previously":[88],"introduced":[89],"extensive-Q":[90,115],"methods.":[92],"Regarding":[93],"complexity":[95],"methods":[98],"computing":[100],"Nash":[101],"equilibrium":[102],"points,":[103],"if":[104],"it":[105],"possible":[107],"assume":[109],"selection":[112],"among":[113],"agents,":[114],"will":[116],"more":[118,126],"convenient":[119],"dynamic":[121],"task":[122],"systems":[124],"than":[127],"agents.":[129]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}