{"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":false,"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":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18895867,"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":31,"referenced_works":["https://openalex.org/W206679605","https://openalex.org/W2026498605","https://openalex.org/W2602275733","https://openalex.org/W2747213132","https://openalex.org/W2761862361","https://openalex.org/W2793780249","https://openalex.org/W2911573951","https://openalex.org/W2913662073","https://openalex.org/W2965163470","https://openalex.org/W2997536466","https://openalex.org/W2998367975","https://openalex.org/W3039736817","https://openalex.org/W3041202696","https://openalex.org/W3155214885","https://openalex.org/W3157603151","https://openalex.org/W3196869853","https://openalex.org/W3209177686","https://openalex.org/W4200120727","https://openalex.org/W4212814156","https://openalex.org/W4213099500","https://openalex.org/W4283714159","https://openalex.org/W4296437512","https://openalex.org/W4306680355","https://openalex.org/W4312295286","https://openalex.org/W4361802167","https://openalex.org/W4381785859","https://openalex.org/W4385245566","https://openalex.org/W4387211792","https://openalex.org/W4388145791","https://openalex.org/W4389170002","https://openalex.org/W4401387035"],"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":[9,77,97,107,119,127,138,173,182],"prospects":[10],"in":[11,22,54,59,101,164],"cooperative":[12,55,64,83],"tasks.":[13],"To":[14,132],"improve":[15],"the":[16,28,41,49,88,93,105,114,123,134,140,145,154,180],"capability":[17],"of":[18,44,63,109,125,156,184],"agent":[19,46,110],"policy":[20,30,75],"new":[23,33],"scenarios,":[24],"some":[25],"transfer":[27,43,61,87,141],"learned":[29],"knowledge":[31,42],"to":[32,103],"scenarios.":[34],"However,":[35],"most":[36],"only":[38],"focus":[39],"on":[40,122,168],"individual":[45],"policies,":[47,111],"neglecting":[48],"credit":[50,78,136],"assignment":[51,79,137],"among":[52],"agents":[53,157],"tasks,":[56],"which":[57],"results":[58,163],"a":[60,71],"bias":[62],"policies.":[65],"In":[66],"this":[67],"paper,":[68],"we":[69,112,143],"propose":[70],"novel":[72],"method,":[73],"transferable":[74],"generation":[76],"(TPGCA)":[80],"network":[81,96,116,149],"for":[82],"MARL.":[84],"TPGCA":[85],"can":[86,152],"entire":[89],"MARL":[90],"model":[91],"by":[92],"constructed":[94],"transferable$Q$-value":[95],"mixing":[98],"network.":[99],"Specifically,":[100],"TPGCA,":[102],"enhance":[104],"effectivity":[106],"transferability":[108,183],"design":[113],"correspondence":[115],"between":[117],"observations":[118],"actions":[120],"(COA)":[121],"basis":[124],"transformer":[126],"gated":[128],"recurrent":[129],"unit":[130],"(GRU).":[131],"implement":[133],"reliable":[135],"diminish":[139],"bias,":[142],"devise":[144],"role-based":[146],"joint$Q$-value":[147],"decomposition":[148],"(RVD)":[150],"that":[151],"evaluate":[153],"contributions":[155],"from":[158],"different":[159],"observation":[160],"perspectives.":[161],"Experimental":[162],"various":[165],"micro-management":[166],"scenarios":[167],"StarCraft":[169],"multiagent":[170,174],"challenge":[171],"(SMAC)":[172],"particle":[175],"environment":[176],"(MPE)":[177],"sufficiently":[178],"demonstrate":[179],"effectiveness":[181],"TPGCA.":[185]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-02-19T00:00:00"}