{"id":"https://openalex.org/W4402353499","doi":"https://doi.org/10.1109/ijcnn60899.2024.10649966","title":"Multi-agent Exploration with Sub-state Entropy Estimation","display_name":"Multi-agent Exploration with Sub-state Entropy Estimation","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402353499","doi":"https://doi.org/10.1109/ijcnn60899.2024.10649966"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10649966","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10649966","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/A5100763092","display_name":"Jian Tao","orcid":"https://orcid.org/0000-0003-4228-6089"},"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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004408878","display_name":"Yangkun Chen","orcid":"https://orcid.org/0000-0001-8274-3921"},"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":"Yangkun Chen","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/A5115596907","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0002-3588-4702"},"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":"Yang Zhang","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/A5100420873","display_name":"Kai Yang","orcid":"https://orcid.org/0000-0002-5983-198X"},"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":"last","author":{"id":"https://openalex.org/A5100754504","display_name":"Xiu Li","orcid":"https://orcid.org/0000-0003-0403-1923"},"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"]}]}],"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":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"70","issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9975000023841858,"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":0.9975000023841858,"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/T12288","display_name":"Optimization and Search Problems","score":0.9940000176429749,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.5562934279441833},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.45984968543052673},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.43290138244628906},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4175356328487396},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4102596640586853},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23017370700836182},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1286832094192505},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12468695640563965},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.10045897960662842},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08043891191482544},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.06799280643463135}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5562934279441833},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.45984968543052673},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.43290138244628906},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4175356328487396},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4102596640586853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23017370700836182},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1286832094192505},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12468695640563965},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.10045897960662842},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08043891191482544},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.06799280643463135}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10649966","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10649966","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1988526405","https://openalex.org/W2017957151","https://openalex.org/W2084176271","https://openalex.org/W2617547828","https://openalex.org/W2626637010","https://openalex.org/W2785738552","https://openalex.org/W2913668833","https://openalex.org/W2948764111","https://openalex.org/W2949475445","https://openalex.org/W2963276097","https://openalex.org/W2963523627","https://openalex.org/W2963762747","https://openalex.org/W2964067469","https://openalex.org/W2970272688","https://openalex.org/W2973229164","https://openalex.org/W2980603164","https://openalex.org/W3011672202","https://openalex.org/W4281784898","https://openalex.org/W4286748781","https://openalex.org/W4287757834","https://openalex.org/W4288594419","https://openalex.org/W4298857966","https://openalex.org/W4299802797","https://openalex.org/W4319653822","https://openalex.org/W4391046127","https://openalex.org/W6637967152","https://openalex.org/W6717230150","https://openalex.org/W6730641667","https://openalex.org/W6735033012","https://openalex.org/W6736209634","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6747473740","https://openalex.org/W6747924173","https://openalex.org/W6755069753","https://openalex.org/W6756303580","https://openalex.org/W6758763022","https://openalex.org/W6758846586","https://openalex.org/W6766805167","https://openalex.org/W6767151588","https://openalex.org/W6769462197","https://openalex.org/W6796436736","https://openalex.org/W6796991022","https://openalex.org/W6809866775","https://openalex.org/W6838308872","https://openalex.org/W6840380725","https://openalex.org/W6861531550"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Researchers":[0],"have":[1],"integrated":[2,151],"exploration":[3,21],"techniques":[4],"into":[5,152],"multi-agent":[6,187],"reinforcement":[7,18,165],"learning":[8],"(MARL)":[9],"algorithms,":[10,156],"drawing":[11],"on":[12,45,66,101,181],"their":[13,34],"remarkable":[14],"success":[15],"in":[16,22,58,184],"deep":[17],"learning.":[19,166],"Nonetheless,":[20],"MARL":[23,155],"presents":[24],"a":[25,42,54,114,144,160],"more":[26],"substantial":[27],"challenge,":[28],"as":[29],"agents":[30,57,79],"need":[31],"to":[32,36,71,80,87,118,127,136],"coordinate":[33],"efforts":[35],"achieve":[37,88],"comprehensive":[38],"state":[39],"coverage.":[40],"Reaching":[41],"unanimous":[43],"agreement":[44],"which":[46,122,157],"kinds":[47],"of":[48,104,177],"states":[49,82],"warrant":[50],"exploring":[51],"can":[52,148,172],"be":[53,149],"struggle":[55],"for":[56,164],"this":[59,73],"context.":[60],"We":[61],"introduce":[62],"Multi-agent":[63],"Exploration":[64],"based":[65,100],"Sub-state":[67],"Entropy":[68],"(MESE":[69],")":[70],"address":[72],"limitation.":[74],"This":[75],"novel":[76],"approach":[77,117],"incentivizes":[78],"explore":[81],"cooperatively":[83],"by":[84],"directing":[85],"them":[86],"consensus":[89],"via":[90],"an":[91],"extra":[92],"team":[93],"reward.":[94,141],"Calculating":[95],"the":[96,102,105,120,129,138,175,185],"additional":[97],"reward":[98],"is":[99,143],"novelty":[103],"current":[106],"sub-state":[107],"that":[108,147,170],"merits":[109],"cooperative":[110],"exploration.":[111],"MESE":[112,142,171],"employs":[113],"conditioned":[115],"entropy":[116,125,130],"select":[119],"sub-state,":[121],"uses":[123,132],"particle-based":[124],"estimation":[126],"calculate":[128,137],"and":[131,179],"Random":[133],"Network":[134],"Distillation(RND)":[135],"team\u2019s":[139],"intrinsic":[140],"plug-and-play":[145],"module":[146],"seamlessly":[150],"most":[153],"existing":[154],"makes":[158],"it":[159],"highly":[161],"effective":[162],"tool":[163],"Our":[167],"experiments":[168],"demonstrate":[169],"substantially":[173],"improve":[174],"performance":[176],"MAPPO":[178],"QMIX":[180],"various":[182],"tasks":[183],"StarCraft":[186],"challenge":[188],"(SMAC).":[189]},"counts_by_year":[{"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"}