{"id":"https://openalex.org/W4385488901","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191336","title":"Curiosity-driven Exploration for Cooperative Multi-Agent Reinforcement Learning","display_name":"Curiosity-driven Exploration for Cooperative Multi-Agent Reinforcement Learning","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385488901","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191336"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191336","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191336","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","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/A5031926389","display_name":"Fanchao Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]},{"id":"https://openalex.org/I14396692","display_name":"Tokyo University of Information Sciences","ror":"https://ror.org/044bdx604","country_code":"JP","type":"education","lineage":["https://openalex.org/I14396692"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Fanchao Xu","raw_affiliation_strings":["Graduate School of Interdisciplinary Information Studies, University of Tokyo,Tokyo,Japan","Graduate School of Interdisciplinary Information Studies, University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Interdisciplinary Information Studies, University of Tokyo,Tokyo,Japan","institution_ids":["https://openalex.org/I14396692","https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Interdisciplinary Information Studies, University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I14396692","https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103172324","display_name":"Tomoyuki Kaneko","orcid":"https://orcid.org/0000-0001-8051-2388"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoyuki Kaneko","raw_affiliation_strings":["Interfaculty Initiative in Information Studies, University of Tokyo,Tokyo,Japan","Interfaculty Initiative in Information Studies, University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Interfaculty Initiative in Information Studies, University of Tokyo,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Interfaculty Initiative in Information Studies, University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031926389"],"corresponding_institution_ids":["https://openalex.org/I14396692","https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.1746,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54452788,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.996999979019165,"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":0.9692999720573425,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.9837517142295837},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7949022054672241},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6783271431922913},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5968586206436157},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.48940935730934143},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.47278499603271484},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4506323039531708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4349229633808136},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14504778385162354},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.0968809425830841}],"concepts":[{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.9837517142295837},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7949022054672241},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6783271431922913},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5968586206436157},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.48940935730934143},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.47278499603271484},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4506323039531708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4349229633808136},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14504778385162354},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0968809425830841},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10191336","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191336","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1641379095","https://openalex.org/W1959608418","https://openalex.org/W2166533447","https://openalex.org/W2292533394","https://openalex.org/W2617547828","https://openalex.org/W2724169821","https://openalex.org/W2747213132","https://openalex.org/W2749807327","https://openalex.org/W2807741983","https://openalex.org/W2947526499","https://openalex.org/W2949963774","https://openalex.org/W2963523627","https://openalex.org/W2963762747","https://openalex.org/W2964067469","https://openalex.org/W2979284752","https://openalex.org/W2996549507","https://openalex.org/W3004640943","https://openalex.org/W3005980215","https://openalex.org/W3046288222","https://openalex.org/W3134226813","https://openalex.org/W3170473100","https://openalex.org/W3211360571","https://openalex.org/W4287755265","https://openalex.org/W4287867830","https://openalex.org/W4288091739","https://openalex.org/W4288594419","https://openalex.org/W4307928265","https://openalex.org/W4313304820","https://openalex.org/W4385245566","https://openalex.org/W6640963894","https://openalex.org/W6687236050","https://openalex.org/W6739901393","https://openalex.org/W6740092555","https://openalex.org/W6752380930","https://openalex.org/W6756303580","https://openalex.org/W6758846586","https://openalex.org/W6762491519","https://openalex.org/W6766805167","https://openalex.org/W6767327128","https://openalex.org/W6769462197","https://openalex.org/W6771807793","https://openalex.org/W6781750019","https://openalex.org/W6784152626","https://openalex.org/W6797584944","https://openalex.org/W6803709789"],"related_works":["https://openalex.org/W3094054656","https://openalex.org/W4285676344","https://openalex.org/W2123270665","https://openalex.org/W4382584175","https://openalex.org/W2060310955","https://openalex.org/W2284924956","https://openalex.org/W3043413210","https://openalex.org/W2613740288","https://openalex.org/W4252460700","https://openalex.org/W4383268304"],"abstract_inverted_index":{"In":[0],"multi-agent":[1,35,39],"reinforcement":[2],"learning,":[3],"exploration":[4,28,41],"is":[5],"more":[6],"challenging":[7],"because":[8],"of":[9,17,56,61],"the":[10,15,34,51,59,67,71,82],"large":[11],"state-action":[12],"space":[13],"and":[14,37,84,95],"requirement":[16],"fine":[18],"cooperation":[19],"among":[20],"multiple":[21],"agents.":[22],"We":[23,43,78],"extend":[24],"ICM,":[25],"a":[26,54],"curiosity-driven":[27,40],"method":[29],"for":[30,53],"single-agent":[31],"environments,":[32],"to":[33,50],"setting":[36],"propose":[38],"(MACDE).":[42],"define":[44],"our":[45],"intrinsic":[46],"reward":[47],"with":[48],"respect":[49],"curiosity":[52,64],"team":[55],"agents":[57],"as":[58],"summation":[60],"individual":[62],"agents'":[63,76],"given":[65],"by":[66],"prediction":[68],"error":[69],"in":[70,81,99],"next":[72],"state":[73],"considering":[74],"other":[75],"actions.":[77],"evaluate":[79],"MACDE":[80,92],"Predator-Prey":[83],"StarCraft":[85],"Multi-Agent":[86],"Challenge.":[87],"The":[88],"results":[89],"show":[90],"that":[91],"worked":[93],"effectively":[94],"learned":[96],"better":[97],"policies":[98],"both":[100],"environments.":[101]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}