{"id":"https://openalex.org/W4414359868","doi":"https://doi.org/10.24963/ijcai.2025/803","title":"CADP: Towards Better Centralized Learning for Decentralized Execution in MARL","display_name":"CADP: Towards Better Centralized Learning for Decentralized Execution in MARL","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359868","doi":"https://doi.org/10.24963/ijcai.2025/803"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/803","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","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/A5048314356","display_name":"Yihe Zhou","orcid":"https://orcid.org/0009-0004-2595-6743"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yihe Zhou","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090854835","display_name":"Shunyu Liu","orcid":"https://orcid.org/0000-0003-0584-9129"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shunyu Liu","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039449527","display_name":"Yunpeng Qing","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunpeng Qing","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113429288","display_name":"Tongya Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114441","display_name":"Zhejiang Provincial Public Security Department","ror":"https://ror.org/01z3tch16","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210114441"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongya Zheng","raw_affiliation_strings":["Zhejiang Provincial Engineering Research Center for Real-Time SmartTech in Urban Security Governance, School of Computer and Computing Science, Hangzhou City University"],"affiliations":[{"raw_affiliation_string":"Zhejiang Provincial Engineering Research Center for Real-Time SmartTech in Urban Security Governance, School of Computer and Computing Science, Hangzhou City University","institution_ids":["https://openalex.org/I4210114441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100632847","display_name":"Kaixuan Chen","orcid":"https://orcid.org/0000-0002-2492-5230"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaixuan Chen","raw_affiliation_strings":["Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security","State Key Laboratory of Blockchain and Data Security, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security","institution_ids":[]},{"raw_affiliation_string":"State Key Laboratory of Blockchain and Data Security, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047371218","display_name":"Jie Song","orcid":"https://orcid.org/0000-0003-3671-6521"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Song","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026532752","display_name":"Mingli Song","orcid":"https://orcid.org/0000-0003-2621-6048"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingli Song","raw_affiliation_strings":["Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security","State Key Laboratory of Blockchain and Data Security, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security","institution_ids":[]},{"raw_affiliation_string":"State Key Laboratory of Blockchain and Data Security, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5048314356"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":3.3332,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.9353355,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7218","last_page":"7226"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9043999910354614,"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"}},"topics":[{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9043999910354614,"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/T11424","display_name":"Security and Verification in Computing","score":0.9024999737739563,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.628600001335144},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6164000034332275},{"id":"https://openalex.org/keywords/decentralised-system","display_name":"Decentralised system","score":0.5706999897956848},{"id":"https://openalex.org/keywords/information-exchange","display_name":"Information exchange","score":0.4341000020503998},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.43309998512268066},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.43070000410079956},{"id":"https://openalex.org/keywords/state-information","display_name":"State information","score":0.3874000012874603},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.3702000081539154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6852999925613403},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.628600001335144},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6164000034332275},{"id":"https://openalex.org/C205875254","wikidata":"https://www.wikidata.org/wiki/Q17156857","display_name":"Decentralised system","level":3,"score":0.5706999897956848},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4984999895095825},{"id":"https://openalex.org/C189693848","wikidata":"https://www.wikidata.org/wiki/Q6031064","display_name":"Information exchange","level":2,"score":0.4341000020503998},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.43309998512268066},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.43070000410079956},{"id":"https://openalex.org/C2985963534","wikidata":"https://www.wikidata.org/wiki/Q7603704","display_name":"State information","level":3,"score":0.3874000012874603},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.3702000081539154},{"id":"https://openalex.org/C2776854237","wikidata":"https://www.wikidata.org/wiki/Q6031064","display_name":"Information sharing","level":2,"score":0.36910000443458557},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C101780184","wikidata":"https://www.wikidata.org/wiki/Q840576","display_name":"Dissemination","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/803","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Centralized":[0,108],"Training":[1],"with":[2,206],"Decentralized":[3,111],"Execution":[4],"(CTDE)":[5],"has":[6],"recently":[7],"emerged":[8],"as":[9],"a":[10,31,106,166,178],"popular":[11],"framework":[12,79,114,201],"for":[13,85,115,135,154],"cooperative":[14,64],"Multi-Agent":[15],"Reinforcement":[16],"Learning":[17],"(MARL),":[18],"where":[19],"agents":[20,60,126,141,153],"can":[21,96],"use":[22],"additional":[23],"global":[24,63,83],"state":[25],"information":[26,65,84],"to":[27,88,146,171],"guide":[28],"training":[29,128],"in":[30,183],"centralized":[32,70,156],"way":[33],"and":[34,93,110,148,192],"make":[35],"their":[36],"own":[37],"decisions":[38],"only":[39,119],"based":[40],"on":[41,55,189],"decentralized":[42,136,162],"local":[43],"policies.":[44],"Despite":[45],"the":[46,76,98,132,142,161,174,199,207],"encouraging":[47],"results":[48],"achieved,":[49],"CTDE":[50,78],"makes":[51],"an":[52,89,121],"independence":[53],"assumption":[54],"agent":[56,175,184],"policies,":[57],"which":[58,95],"limits":[59],"from":[61,66,151],"adopting":[62],"each":[67],"other":[68],"during":[69,127],"training.":[71,157],"Therefore,":[72],"we":[73,104,164],"argue":[74],"that":[75,117,198],"existing":[77],"cannot":[80],"fully":[81],"utilize":[82],"training,":[86],"leading":[87],"inefficient":[90],"joint":[91],"exploration":[92],"perception,":[94],"degrade":[97],"final":[99],"performance.":[100],"In":[101],"this":[102],"paper,":[103],"introduce":[105],"novel":[107],"Advising":[109],"Pruning":[112],"(CADP)":[113],"MARL,":[116],"not":[118],"enables":[120],"efficacious":[122],"message":[123],"exchange":[124],"among":[125],"but":[129],"also":[130],"guarantees":[131],"independent":[133],"policies":[134],"execution.":[137],"Firstly,":[138],"CADP":[139],"endows":[140],"explicit":[143],"communication":[144,176],"channel":[145],"seek":[147],"take":[149],"advice":[150],"different":[152,190],"more":[155],"To":[158],"further":[159],"ensure":[160],"execution,":[163],"propose":[165],"smooth":[167],"model":[168],"pruning":[169],"mechanism":[170],"progressively":[172],"constrain":[173],"into":[177],"closed":[179],"one":[180],"without":[181],"degradation":[182],"cooperation":[185],"capability.":[186],"Empirical":[187],"evaluations":[188],"benchmarks":[191],"across":[193],"various":[194],"MARL":[195],"backbones":[196],"demonstrate":[197],"proposed":[200],"achieves":[202],"superior":[203],"performance":[204],"compared":[205],"state-of-the-art":[208],"counterparts.":[209],"Our":[210],"code":[211],"is":[212],"available":[213],"at":[214],"https://github.com/zyh1999/CADP":[215]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}
