{"id":"https://openalex.org/W7130348084","doi":"https://doi.org/10.1109/tcss.2025.3628971","title":"TPGCA: Transferable Policy Generation and Credit Assignment Network for Cooperative Multiagent Reinforcement Learning","display_name":"TPGCA: Transferable Policy Generation and Credit Assignment Network for Cooperative Multiagent Reinforcement Learning","publication_year":2026,"publication_date":"2026-02-18","ids":{"openalex":"https://openalex.org/W7130348084","doi":"https://doi.org/10.1109/tcss.2025.3628971"},"language":null,"primary_location":{"id":"doi:10.1109/tcss.2025.3628971","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcss.2025.3628971","pdf_url":null,"source":{"id":"https://openalex.org/S2490693980","display_name":"IEEE Transactions on Computational Social Systems","issn_l":"2329-924X","issn":["2329-924X","2373-7476"],"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 Computational Social Systems","raw_type":"journal-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/A5071516934","display_name":"W. J. Li","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Li","raw_affiliation_strings":["School of Instrument Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-9235-9429","affiliations":[{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126288616","display_name":"Jiali Lv","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiali Lv","raw_affiliation_strings":["School of Instrument Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0003-2706-5613","affiliations":[{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hongming Liu","orcid":"https://orcid.org/0009-0002-4305-7309"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongming Liu","raw_affiliation_strings":["School of Instrument Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0002-4305-7309","affiliations":[{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kaizhu Huang","orcid":"https://orcid.org/0000-0002-3034-9639"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaizhu Huang","raw_affiliation_strings":["Digital Innovation Research Center, Duke Kunshan University, Kunshan, China"],"raw_orcid":"https://orcid.org/0000-0002-3034-9639","affiliations":[{"raw_affiliation_string":"Digital Innovation Research Center, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048327458","display_name":"Aiguo Song","orcid":"https://orcid.org/0000-0002-1982-6780"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aiguo Song","raw_affiliation_strings":["School of Instrument Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-1982-6780","affiliations":[{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5071516934"],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33877455,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":"2","first_page":"2557","last_page":"2571"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8567000031471252,"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":0.8567000031471252,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.026100000366568565,"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":0.0203000009059906,"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":0.7439000010490417},{"id":"https://openalex.org/keywords/transferability","display_name":"Transferability","score":0.7267000079154968},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4875999987125397},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.38589999079704285},{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.36399999260902405},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.33799999952316284}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7439000010490417},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.7267000079154968},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6836000084877014},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4875999987125397},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37400001287460327},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.36399999260902405},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.3377000093460083},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2992999851703644},{"id":"https://openalex.org/C81302675","wikidata":"https://www.wikidata.org/wiki/Q7834034","display_name":"Transferable utility","level":3,"score":0.2840999960899353},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2840000092983246},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C63882131","wikidata":"https://www.wikidata.org/wiki/Q17122954","display_name":"Strengths and weaknesses","level":2,"score":0.2614000141620636}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcss.2025.3628971","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcss.2025.3628971","pdf_url":null,"source":{"id":"https://openalex.org/S2490693980","display_name":"IEEE Transactions on Computational Social Systems","issn_l":"2329-924X","issn":["2329-924X","2373-7476"],"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 Computational Social Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multiagent":[0],"reinforcement":[1],"learning":[2,21],"(MARL)":[3],"methods":[4,26,37],"have":[5],"good":[6],"application":[7],"performances":[8],"and":[9,77,101,111,123,131,142,181,190],"prospects":[10],"in":[11,22,54,59,105,172],"cooperative":[12,55,64,83],"tasks.":[13],"To":[14,136],"improve":[15],"the":[16,28,41,49,88,93,109,118,127,138,144,149,162,188],"capability":[17],"of":[18,44,63,113,129,164,192],"agent":[19,46,114],"policy":[20,30,75],"new":[23,33],"scenarios,":[24],"some":[25],"transfer":[27,43,61,87,145],"learned":[29],"knowledge":[31,42],"to":[32,107],"scenarios.":[34],"However,":[35],"most":[36],"only":[38],"focus":[39],"on":[40,126,176],"individual":[45],"policies,":[47,115],"neglecting":[48],"credit":[50,78,140],"assignment":[51,79,141],"among":[52],"agents":[53,165],"tasks,":[56],"which":[57],"results":[58,171],"a":[60,71],"bias":[62],"policies.":[65],"In":[66],"this":[67],"paper,":[68],"we":[69,116,147],"propose":[70],"novel":[72],"method,":[73],"transferable":[74,95],"generation":[76],"(TPGCA)":[80],"network":[81,100,120,157],"for":[82],"MARL.":[84],"TPGCA":[85],"can":[86,160],"entire":[89],"MARL":[90],"model":[91],"by":[92],"constructed":[94],"<inline-formula":[96,152],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[97,153],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[98,154],"notation=\"LaTeX\">$Q$</tex-math></inline-formula>-value":[99,155],"mixing":[102],"network.":[103],"Specifically,":[104],"TPGCA,":[106],"enhance":[108],"effectivity":[110],"transferability":[112,191],"design":[117],"correspondence":[119],"between":[121],"observations":[122],"actions":[124],"(COA)":[125],"basis":[128],"transformer":[130],"gated":[132],"recurrent":[133],"unit":[134],"(GRU).":[135],"implement":[137],"reliable":[139],"diminish":[143],"bias,":[146],"devise":[148],"role-based":[150],"joint":[151],"decomposition":[156],"(RVD)":[158],"that":[159],"evaluate":[161],"contributions":[163],"from":[166],"different":[167],"observation":[168],"perspectives.":[169],"Experimental":[170],"various":[173],"micro-management":[174],"scenarios":[175],"StarCraft":[177],"multiagent":[178,182],"challenge":[179],"(SMAC)":[180],"particle":[183],"environment":[184],"(MPE)":[185],"sufficiently":[186],"demonstrate":[187],"effectiveness":[189],"TPGCA.":[193]},"counts_by_year":[],"updated_date":"2026-04-03T16:38:21.277918","created_date":"2026-02-19T00:00:00"}