{"id":"https://openalex.org/W4388878401","doi":"https://doi.org/10.1109/tcyb.2023.3328732","title":"WToE: Learning When to Explore in Multiagent Reinforcement Learning","display_name":"WToE: Learning When to Explore in Multiagent Reinforcement Learning","publication_year":2023,"publication_date":"2023-11-21","ids":{"openalex":"https://openalex.org/W4388878401","doi":"https://doi.org/10.1109/tcyb.2023.3328732","pmid":"https://pubmed.ncbi.nlm.nih.gov/37988210"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2023.3328732","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2023.3328732","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cybernetics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5086990087","display_name":"Shaokang Dong","orcid":"https://orcid.org/0000-0002-8493-1501"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaokang Dong","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-8493-1501","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076505011","display_name":"Hangyu Mao","orcid":"https://orcid.org/0000-0002-4499-7581"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hangyu Mao","raw_affiliation_strings":["Smart City Group, SenseTime Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4499-7581","affiliations":[{"raw_affiliation_string":"Smart City Group, SenseTime Research, Beijing, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100764370","display_name":"Shangdong Yang","orcid":"https://orcid.org/0000-0001-5379-9539"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]},{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangdong Yang","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","Guangxi Key Lab of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"Guangxi Key Lab of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001095997","display_name":"Shengyu Zhu","orcid":"https://orcid.org/0000-0001-9793-662X"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengyu Zhu","raw_affiliation_strings":["Noah&#x2019;s Ark Lab, Huawei Technologies, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9793-662X","affiliations":[{"raw_affiliation_string":"Noah&#x2019;s Ark Lab, Huawei Technologies, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100462996","display_name":"Wenbin Li","orcid":"https://orcid.org/0000-0002-0935-7124"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbin Li","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-0935-7124","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047509839","display_name":"Jianye Hao","orcid":"https://orcid.org/0000-0002-0422-8235"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]},{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianye Hao","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China","Noah's Ark Lab, Huawei Technologies, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0422-8235","affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Noah's Ark Lab, Huawei Technologies, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074250521","display_name":"Yang Gao","orcid":"https://orcid.org/0000-0002-2488-1813"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Gao","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-2488-1813","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5863,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.86232453,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"54","issue":"8","first_page":"4789","last_page":"4801"},"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9864000082015991,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9861999750137329,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7649833559989929},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7622108459472656},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5717430114746094},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5430516600608826},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4959438741207123},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.46986421942710876},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.4583953619003296},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45077136158943176},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4484168291091919},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.43428322672843933},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3720077872276306},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07671058177947998},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07198664546012878}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7649833559989929},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7622108459472656},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5717430114746094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5430516600608826},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4959438741207123},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.46986421942710876},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4583953619003296},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45077136158943176},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4484168291091919},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.43428322672843933},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3720077872276306},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07671058177947998},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07198664546012878},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2023.3328732","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2023.3328732","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cybernetics","raw_type":"journal-article"},{"id":"pmid:37988210","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37988210","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on cybernetics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/15"}],"awards":[{"id":"https://openalex.org/G1382483900","display_name":null,"funder_award_id":"2021Szvup056","funder_id":"https://openalex.org/F4320329791","funder_display_name":"Shenzhen Fundamental Research Program"},{"id":"https://openalex.org/G2339888215","display_name":null,"funder_award_id":"62106100","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2767813700","display_name":null,"funder_award_id":"62192783","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G325098684","display_name":null,"funder_award_id":"92370132","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7153191022","display_name":null,"funder_award_id":"BK20221441","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G7334411499","display_name":null,"funder_award_id":"62206133","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7551145346","display_name":null,"funder_award_id":"BE2021028","funder_id":"https://openalex.org/F4320327777","funder_display_name":"Jiangsu Provincial Key Research and Development Program"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327777","display_name":"Jiangsu Provincial Key Research and Development Program","ror":null},{"id":"https://openalex.org/F4320329791","display_name":"Shenzhen Fundamental Research Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1977655452","https://openalex.org/W1988526405","https://openalex.org/W2107464055","https://openalex.org/W2168359464","https://openalex.org/W2485926893","https://openalex.org/W2766447205","https://openalex.org/W2768779900","https://openalex.org/W2799151646","https://openalex.org/W2908261578","https://openalex.org/W2919912236","https://openalex.org/W2963523627","https://openalex.org/W2963934958","https://openalex.org/W2982316857","https://openalex.org/W2999963940","https://openalex.org/W3044015199","https://openalex.org/W3092253573","https://openalex.org/W3092804041","https://openalex.org/W3112197505","https://openalex.org/W3195143297","https://openalex.org/W4319165238","https://openalex.org/W6634907821","https://openalex.org/W6640044251","https://openalex.org/W6676833704","https://openalex.org/W6679661297","https://openalex.org/W6716474083","https://openalex.org/W6717230150","https://openalex.org/W6735033012","https://openalex.org/W6738796088","https://openalex.org/W6740092555","https://openalex.org/W6746523204","https://openalex.org/W6747473740","https://openalex.org/W6750186571","https://openalex.org/W6752725515","https://openalex.org/W6755625160","https://openalex.org/W6756303580","https://openalex.org/W6758507868","https://openalex.org/W6758641611","https://openalex.org/W6767151588","https://openalex.org/W6767327128","https://openalex.org/W6769462197","https://openalex.org/W6771807793","https://openalex.org/W6779410211","https://openalex.org/W6780218565","https://openalex.org/W6800937065","https://openalex.org/W6853529480"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W2382997850","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548"],"abstract_inverted_index":{"Existing":[0],"multiagent":[1,149],"exploration":[2,41,54,114,144,171],"works":[3],"focus":[4],"on":[5],"how":[6],"to":[7,33,43,56,58,74,96,105],"explore":[8],"in":[9,17,113,146],"the":[10,18,76,90,108,116,122,131,134,153,162],"fully":[11],"cooperative":[12],"task,":[13],"which":[14],"is":[15],"insufficient":[16],"environment":[19],"with":[20,107],"nonstationarity":[21],"induced":[22],"by":[23],"agent":[24],"interactions.":[25],"To":[26],"tackle":[27],"this":[28,85],"issue,":[29],"we":[30,88,141],"propose":[31,63],"When":[32],"Explore":[34],"(WToE),":[35],"a":[36,64,70,98],"simple":[37],"yet":[38],"effective":[39],"variational":[40,92],"method":[42],"learn":[44],"WToE":[45,49,165],"under":[46],"nonstationary":[47],"environments.":[48,158],"employs":[50],"an":[51],"interaction-oriented":[52],"adaptive":[53],"mechanism":[55,145],"adapt":[57],"environmental":[59,78],"changes.":[60],"We":[61],"first":[62],"novel":[65],"graphical":[66,86],"model":[67,75],"that":[68],"uses":[69],"latent":[71],"random":[72],"variable":[73],"step-level":[77],"change":[79],"resulting":[80],"from":[81,102,121],"interaction":[82],"effects.":[83],"Leveraging":[84],"model,":[87],"employ":[89],"supervised":[91],"auto-encoder":[93],"(VAE)":[94],"framework":[95],"derive":[97],"short-term":[99,117],"inferred":[100,118],"policy":[101,119],"historical":[103],"trajectories":[104],"deal":[106],"nonstationarity.":[109],"Finally,":[110],"agents":[111],"engage":[112],"when":[115],"diverges":[120],"current":[123],"actor":[124],"policy.":[125],"The":[126,159],"proposed":[127],"approach":[128],"theoretically":[129],"guarantees":[130],"convergence":[132],"of":[133,156,164],"Q":[135],"-value":[136],"function.":[137],"In":[138],"our":[139,143],"experiments,":[140],"validate":[142],"grid":[147],"examples,":[148],"particle":[150],"environments":[151],"and":[152,169,178],"battle":[154],"game":[155],"MAgent":[157],"results":[160],"demonstrate":[161],"superiority":[163],"over":[166],"multiple":[167],"baselines":[168],"existing":[170],"methods,":[172],"such":[173],"as":[174],"MAEXQ,":[175],"NoisyNets,":[176],"EITI,":[177],"PR2.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
