{"id":"https://openalex.org/W4385767442","doi":"https://doi.org/10.24963/ijcai.2023/39","title":"Dynamic Belief for Decentralized Multi-Agent Cooperative Learning","display_name":"Dynamic Belief for Decentralized Multi-Agent Cooperative Learning","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385767442","doi":"https://doi.org/10.24963/ijcai.2023/39"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/39","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/39","pdf_url":"https://www.ijcai.org/proceedings/2023/0039.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0039.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045281526","display_name":"Yunpeng Zhai","orcid":"https://orcid.org/0000-0003-2246-8045"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunpeng Zhai","raw_affiliation_strings":["National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070755370","display_name":"Peixi Peng","orcid":"https://orcid.org/0000-0002-7427-8764"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peixi Peng","raw_affiliation_strings":["National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China","Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100367520","display_name":"Su Chen","orcid":"https://orcid.org/0000-0003-0264-8831"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Su","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School, Shenzhen, China","National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023918894","display_name":"Yonghong Tian","orcid":"https://orcid.org/0000-0002-2978-5935"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghong Tian","raw_affiliation_strings":["National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China","Peng Cheng Laboratory, Shenzhen, China","School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3263,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64690538,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"344","last_page":"352"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9984999895095825,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9965000152587891,"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/inference","display_name":"Inference","score":0.7922109365463257},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.775973916053772},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7258272171020508},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.6404660940170288},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6268529891967773},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5930374264717102},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5722372531890869},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4429640471935272},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4338294267654419},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09527504444122314}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7922109365463257},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.775973916053772},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7258272171020508},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.6404660940170288},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6268529891967773},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5930374264717102},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5722372531890869},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4429640471935272},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4338294267654419},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09527504444122314},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/39","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/39","pdf_url":"https://www.ijcai.org/proceedings/2023/0039.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/39","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/39","pdf_url":"https://www.ijcai.org/proceedings/2023/0039.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3833898155","display_name":null,"funder_award_id":"62088102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4587952244","display_name":null,"funder_award_id":"62027804","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6166162970","display_name":null,"funder_award_id":"No. 61825101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6662223526","display_name":null,"funder_award_id":"61825101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7025311388","display_name":null,"funder_award_id":"No. 62088102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8836417728","display_name":null,"funder_award_id":"No. 62027804","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385767442.pdf"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1641379095","https://openalex.org/W1959608418","https://openalex.org/W2012812921","https://openalex.org/W2120327309","https://openalex.org/W2292533394","https://openalex.org/W2344944957","https://openalex.org/W2475089067","https://openalex.org/W2601322194","https://openalex.org/W2617547828","https://openalex.org/W2626637010","https://openalex.org/W2736601468","https://openalex.org/W2747213132","https://openalex.org/W2776777826","https://openalex.org/W2912563296","https://openalex.org/W2949963774","https://openalex.org/W2950397026","https://openalex.org/W2951326654","https://openalex.org/W2963065757","https://openalex.org/W2963715810","https://openalex.org/W2963809389","https://openalex.org/W2964338167","https://openalex.org/W2965433979","https://openalex.org/W2980061931","https://openalex.org/W2980433389","https://openalex.org/W3035478219","https://openalex.org/W3046288222","https://openalex.org/W3089778445","https://openalex.org/W3099689767","https://openalex.org/W3119866505","https://openalex.org/W3128901210","https://openalex.org/W3169291081","https://openalex.org/W3174487171","https://openalex.org/W3175698408","https://openalex.org/W3193434518","https://openalex.org/W4200632533","https://openalex.org/W4226016097","https://openalex.org/W4283032009","https://openalex.org/W4286748781","https://openalex.org/W4287079499","https://openalex.org/W4287126489","https://openalex.org/W4287391697","https://openalex.org/W4287394326","https://openalex.org/W4287899365","https://openalex.org/W4288594419","https://openalex.org/W4295598622","https://openalex.org/W4299802797","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2055243143","https://openalex.org/W4321636575","https://openalex.org/W1986418932","https://openalex.org/W2357796999","https://openalex.org/W2045526782","https://openalex.org/W2741131631","https://openalex.org/W2156919374","https://openalex.org/W1483472507","https://openalex.org/W1984019423","https://openalex.org/W4280588203"],"abstract_inverted_index":{"Decentralized":[0],"multi-agent":[1,38],"cooperative":[2],"learning":[3,54],"is":[4,39],"a":[5,64,98,108,117,126],"practical":[6],"task":[7,139],"due":[8,43],"to":[9,22,26,44,62,71,90,101,107,121],"the":[10,27,34,73,82,91,103,134,147,155],"partially":[11],"observed":[12],"setting":[13],"both":[14],"in":[15,53,146],"training":[16,36,149],"and":[17,29,79,116,141,151],"execution.":[18],"Every":[19],"agent":[20,70],"learns":[21],"cooperate":[23],"without":[24],"access":[25],"observations":[28],"policies":[30,50,75,124],"of":[31,37,40,76,84,93,113],"others.":[32],"However,":[33],"decentralized":[35,148],"great":[41],"difficulty":[42],"non-stationarity,":[45],"especially":[46],"when":[47],"other":[48,77,114],"agents'":[49],"are":[51],"also":[52],"during":[55],"training.":[56],"To":[57,87],"overcome":[58],"this,":[59],"we":[60,96],"propose":[61],"learn":[63,102],"dynamic":[65],"policy":[66,83],"belief":[67,104],"for":[68],"each":[69],"predict":[72],"current":[74],"agents":[78,115],"accordingly":[80],"condition":[81],"its":[85,143],"own.":[86],"quickly":[88],"adapt":[89],"development":[92],"others'":[94],"policies,":[95],"introduce":[97],"historical":[99],"context":[100],"inference":[105,120],"according":[106],"few":[109],"recent":[110],"action":[111],"histories":[112],"latent":[118],"variational":[119],"model":[122],"their":[123],"by":[125],"learned":[127],"distribution.":[128],"We":[129],"evaluate":[130],"our":[131],"method":[132],"on":[133],"StarCraft":[135],"II":[136],"micro":[137],"management":[138],"(SMAC)":[140],"demonstrate":[142],"superior":[144],"performance":[145],"settings":[150],"comparable":[152],"results":[153],"with":[154],"state-of-the-art":[156],"CTDE":[157],"methods.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}