{"id":"https://openalex.org/W4291653308","doi":"https://doi.org/10.1109/access.2022.3198981","title":"CuMARL: Curiosity-Based Learning in Multiagent Reinforcement Learning","display_name":"CuMARL: Curiosity-Based Learning in Multiagent Reinforcement Learning","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4291653308","doi":"https://doi.org/10.1109/access.2022.3198981"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3198981","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3198981","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2022.3198981","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080626085","display_name":"Devarani Devi Ningombam","orcid":"https://orcid.org/0000-0002-6946-6584"},"institutions":[{"id":"https://openalex.org/I5847235","display_name":"University of Petroleum and Energy Studies","ror":"https://ror.org/04q2jes40","country_code":"IN","type":"education","lineage":["https://openalex.org/I5847235"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Devarani Devi Ningombam","raw_affiliation_strings":["Department of Informatics, School of Computer Science, University of Petroleum and Energy Studies (UPES), Dehradun, Uttarakhand, India"],"raw_orcid":"https://orcid.org/0000-0002-6946-6584","affiliations":[{"raw_affiliation_string":"Department of Informatics, School of Computer Science, University of Petroleum and Energy Studies (UPES), Dehradun, Uttarakhand, India","institution_ids":["https://openalex.org/I5847235"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071461874","display_name":"Byunghyun Yoo","orcid":"https://orcid.org/0000-0003-0857-5565"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byunghyun Yoo","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-0857-5565","affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330218","display_name":"Hyun Woo Kim","orcid":"https://orcid.org/0000-0003-2473-8360"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyun Woo Kim","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034406505","display_name":"Hwa Jeon Song","orcid":"https://orcid.org/0000-0002-8216-4812"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hwa Jeon Song","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-8216-4812","affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085539609","display_name":"Sungwon Yi","orcid":"https://orcid.org/0000-0002-4986-9546"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungwon Yi","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-4986-9546","affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.6648,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.86408744,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"10","issue":null,"first_page":"87254","last_page":"87265"},"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9578999876976013,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9480999708175659,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/curiosity","display_name":"Curiosity","score":0.8079643845558167},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7705708742141724},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.756662905216217},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.504562497138977},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.4544009864330292},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.44846946001052856},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3381040096282959},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07611367106437683}],"concepts":[{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.8079643845558167},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7705708742141724},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.756662905216217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.504562497138977},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.4544009864330292},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.44846946001052856},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3381040096282959},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07611367106437683},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2022.3198981","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3198981","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:ea341c98ba52493b8fe43c46f77bd8a6","is_oa":true,"landing_page_url":"https://doaj.org/article/ea341c98ba52493b8fe43c46f77bd8a6","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 10, Pp 87254-87265 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3198981","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3198981","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8199999928474426}],"awards":[{"id":"https://openalex.org/G6753616810","display_name":null,"funder_award_id":"FA2386-19-1-4020","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320322093","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W326419249","https://openalex.org/W2135635111","https://openalex.org/W2164424353","https://openalex.org/W2592798481","https://openalex.org/W2803728337","https://openalex.org/W2914351253","https://openalex.org/W2949475445","https://openalex.org/W2949963774","https://openalex.org/W2950993296","https://openalex.org/W2963276097","https://openalex.org/W2963523627","https://openalex.org/W2965870268","https://openalex.org/W2970272688","https://openalex.org/W2980225636","https://openalex.org/W2997343068","https://openalex.org/W2997940961","https://openalex.org/W3015873116","https://openalex.org/W3046082509","https://openalex.org/W3046288222","https://openalex.org/W3091517403","https://openalex.org/W3129153311","https://openalex.org/W3198965389","https://openalex.org/W3211360571","https://openalex.org/W4241795126","https://openalex.org/W4287755265","https://openalex.org/W4288359891","https://openalex.org/W4288594419","https://openalex.org/W4293586424","https://openalex.org/W4295598622","https://openalex.org/W6717230150","https://openalex.org/W6730641667","https://openalex.org/W6734678876","https://openalex.org/W6748311529","https://openalex.org/W6749304979","https://openalex.org/W6751971351","https://openalex.org/W6754779100","https://openalex.org/W6758763022","https://openalex.org/W6758846586","https://openalex.org/W6761920647","https://openalex.org/W6762491519","https://openalex.org/W6767151588","https://openalex.org/W6781750019","https://openalex.org/W6784152626","https://openalex.org/W6803709789"],"related_works":["https://openalex.org/W2371091044","https://openalex.org/W2171010636","https://openalex.org/W87513465","https://openalex.org/W2786230833","https://openalex.org/W1966803121","https://openalex.org/W2391666574","https://openalex.org/W3203256658","https://openalex.org/W2352650970","https://openalex.org/W1544514152","https://openalex.org/W1493952344"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,53,86],"propose":[4],"a":[5,77,88],"novel":[6],"curiosity-based":[7],"learning":[8,74],"algorithm":[9,102],"for":[10,66],"Multi-agent":[11],"Reinforcement":[12],"Learning":[13,150],"(MARL)":[14],"to":[15,71,134],"attain":[16],"efficient":[17],"and":[18,31,60,149],"effective":[19],"decision-making.":[20],"We":[21,95],"employ":[22],"the":[23,39,47,62,97,100,115,124,129,141],"centralized":[24],"training":[25],"with":[26],"decentralized":[27],"execution":[28],"framework":[29],"(CTDE)":[30],"consider":[32,87],"that":[33,123],"each":[34],"agent":[35],"has":[36],"knowledge":[37],"of":[38,43,64,93,99,107],"prior":[40],"action":[41],"distribution":[42],"others.":[44],"To":[45],"quantify":[46],"difference":[48],"in":[49,76,103],"agents\u2019":[50],"knowledge,":[51],"curiosity,":[52],"introduce":[54],"conditional":[55],"mutual":[56],"information":[57,65],"(CMI)":[58],"regularization":[59],"use":[61],"amount":[63],"updating":[67],"decision-making":[68],"policy.":[69],"Then,":[70],"deploy":[72],"these":[73],"frameworks":[75],"large-scale":[78],"MARL":[79,137],"setting":[80],"while":[81],"acquiring":[82],"high":[83],"sample":[84],"efficiency,":[85],"Kullback-Leibler":[89],"(KL)":[90],"divergence-based":[91],"prioritization":[92],"experiences.":[94],"evaluate":[96],"effectiveness":[98],"proposed":[101,125],"three":[104],"different":[105],"levels":[106],"StarCraft":[108],"Multi":[109],"Agent":[110],"Challenge":[111],"(SMAC)":[112],"scenarios":[113],"using":[114],"PyMARL":[116],"framework.":[117],"The":[118],"simulation-based":[119],"performance":[120],"analysis":[121],"shows":[122],"technique":[126],"significantly":[127],"improves":[128],"test":[130],"win":[131],"rate":[132],"compared":[133],"various":[135],"state-of-the-art":[136],"benchmarks,":[138],"such":[139],"as":[140],"Optimistically":[142],"Weighted":[143],"Monotonic":[144],"Value":[145],"Function":[146],"Factorization":[147],"(OW_QMIX)":[148],"Individual":[151],"Intrinsic":[152],"Reward":[153],"(LIIR).":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}