{"id":"https://openalex.org/W4402352238","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650769","title":"CMBE: Curiosity-driven Model-Based Exploration for Multi-Agent Reinforcement Learning in Sparse Reward Settings","display_name":"CMBE: Curiosity-driven Model-Based Exploration for Multi-Agent Reinforcement Learning in Sparse Reward Settings","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402352238","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650769"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650769","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5115589268","display_name":"Kai Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yang","raw_affiliation_strings":["Tsinghua University,Tsinghua Shenzhen International Graduate School"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua Shenzhen International Graduate School","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113373670","display_name":"Zhirui Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhirui Fang","raw_affiliation_strings":["Tsinghua University,Tsinghua Shenzhen International Graduate School"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua Shenzhen International Graduate School","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082207156","display_name":"Xiu Li","orcid":"https://orcid.org/0000-0001-6906-6735"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiu Li","raw_affiliation_strings":["Tsinghua University,Tsinghua Shenzhen International Graduate School"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua Shenzhen International Graduate School","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112998095","display_name":"Jian Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Tao","raw_affiliation_strings":["Tsinghua University,Tsinghua Shenzhen International Graduate School"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua Shenzhen International Graduate School","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9983999729156494,"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":0.9983999729156494,"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/T11031","display_name":"Game Theory and Applications","score":0.9060999751091003,"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/curiosity","display_name":"Curiosity","score":0.9285834431648254},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7793599367141724},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7247998714447021},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5139262676239014},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3645303249359131},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3402683138847351},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.19038686156272888},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.07603111863136292}],"concepts":[{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.9285834431648254},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7793599367141724},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7247998714447021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5139262676239014},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3645303249359131},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3402683138847351},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.19038686156272888},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.07603111863136292}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650769","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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":45,"referenced_works":["https://openalex.org/W779494576","https://openalex.org/W2617547828","https://openalex.org/W2626637010","https://openalex.org/W2747213132","https://openalex.org/W2788455270","https://openalex.org/W2883550421","https://openalex.org/W2885550588","https://openalex.org/W2949475445","https://openalex.org/W2963276097","https://openalex.org/W2963359646","https://openalex.org/W2963523627","https://openalex.org/W2963762747","https://openalex.org/W2964067469","https://openalex.org/W2996549507","https://openalex.org/W2997289589","https://openalex.org/W3034971464","https://openalex.org/W3046288222","https://openalex.org/W3170473100","https://openalex.org/W3211360571","https://openalex.org/W4286748781","https://openalex.org/W4287755265","https://openalex.org/W4287758406","https://openalex.org/W4288091739","https://openalex.org/W4288594419","https://openalex.org/W4297791094","https://openalex.org/W4299802797","https://openalex.org/W4379919360","https://openalex.org/W4382202977","https://openalex.org/W4385482713","https://openalex.org/W4391046127","https://openalex.org/W4402353499","https://openalex.org/W6717230150","https://openalex.org/W6730641667","https://openalex.org/W6734517396","https://openalex.org/W6738796088","https://openalex.org/W6762491519","https://openalex.org/W6766805167","https://openalex.org/W6767327128","https://openalex.org/W6779101081","https://openalex.org/W6784152626","https://openalex.org/W6796991022","https://openalex.org/W6797584944","https://openalex.org/W6803709789","https://openalex.org/W6839595714","https://openalex.org/W6840380725"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Sparse":[0],"rewards":[1],"in":[2,19,70,112,122,151,172,195],"reinforcement":[3,54],"learning":[4,34,55],"have":[5],"long":[6],"been":[7],"a":[8,48,146,173],"central":[9],"research":[10],"challenge,":[11],"often":[12],"tackled":[13],"through":[14],"various":[15],"exploration":[16,37,50,69,77,93],"methods.":[17,65],"However,":[18],"multi-agent":[20,53],"scenarios":[21],"with":[22,119,136],"larger":[23],"state":[24,81,126,138],"spaces":[25],"and":[26,31,63,128],"action":[27],"spaces,":[28],"sparser":[29],"rewards,":[30],"more":[32,137],"complex":[33],"strategies,":[35],"conventional":[36],"methods":[38],"cannot":[39],"achieve":[40],"satisfactory":[41],"results.":[42],"In":[43],"this":[44,161],"paper,":[45],"we":[46,140,163,177],"introduce":[47],"novel":[49],"approach":[51,194],"for":[52],"that":[56],"combines":[57],"the":[58,71,79,86,91,110,113,116,123,129,133,142,149,152,158,179,186,190],"strengths":[59],"of":[60,78,115,125,132,148,160,181,185,192],"model-based":[61],"techniques":[62],"curiosity-driven":[64,68,117,143],"We":[66],"use":[67],"early":[72],"stages":[73],"to":[74,97,104,109,168],"facilitate":[75],"comprehensive":[76],"entire":[80],"space.":[82],"As":[83],"training":[84],"progresses,":[85],"forward":[87,134,153],"model,":[88],"trained":[89],"during":[90],"initial":[92],"phase,":[94],"is":[95],"employed":[96],"selectively":[98],"explore":[99],"crucial":[100],"actions,":[101],"allowing":[102],"agents":[103],"discover":[105],"effective":[106],"strategies.":[107],"Due":[108],"decrease":[111],"loss":[114,144],"method":[118],"an":[120],"increase":[121],"number":[124],"visits":[127],"increasing":[130],"accuracy":[131],"model":[135],"visits,":[139],"utilize":[141],"as":[145],"measure":[147],"uncertainty":[150],"model.":[154],"Subsequently,":[155],"based":[156],"on":[157],"magnitude":[159],"uncertainty,":[162],"determine":[164],"which":[165],"intrinsic":[166],"reward":[167],"employ.":[169],"Through":[170],"experiments":[171],"sparse-reward":[174],"SMAC":[175],"environment,":[176],"demonstrate":[178],"effectiveness":[180],"our":[182,193],"algorithm.":[183],"Visualizations":[184],"results":[187],"further":[188],"validate":[189],"efficacy":[191],"enhancing":[196],"exploration.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}