{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T21:02:40Z","timestamp":1775250160751,"version":"3.50.1"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Open Fund of Key Laboratory of the Ministry of Education on Artificial Intelligence in Equipment","award":["2024-AAIE-KF03-01"],"award-info":[{"award-number":["2024-AAIE-KF03-01"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput. Soc. Syst."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tcss.2025.3628971","type":"journal-article","created":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T21:21:57Z","timestamp":1771449717000},"page":"2557-2571","source":"Crossref","is-referenced-by-count":0,"title":["TPGCA: Transferable Policy Generation and Credit Assignment Network for Cooperative Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9235-9429","authenticated-orcid":false,"given":"Wei","family":"Li","sequence":"first","affiliation":[{"name":"School of Instrument Science and Engineering, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2706-5613","authenticated-orcid":false,"given":"Jiali","family":"Lv","sequence":"additional","affiliation":[{"name":"School of Instrument Science and Engineering, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4305-7309","authenticated-orcid":false,"given":"Hongming","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Instrument Science and Engineering, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3034-9639","authenticated-orcid":false,"given":"Kaizhu","family":"Huang","sequence":"additional","affiliation":[{"name":"Digital Innovation Research Center, Duke Kunshan University, Kunshan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1982-6780","authenticated-orcid":false,"given":"Aiguo","family":"Song","sequence":"additional","affiliation":[{"name":"School of Instrument Science and Engineering, Southeast University, Nanjing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2894403"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2021.3122282"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2022.3144978"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2021.3074038"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2023.3329990"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2760281"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2018.2811376"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/65"},{"key":"ref9","first-page":"24611","article-title":"The surprising effectiveness of MAPPO in cooperative multi-agent games","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Yu","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2023.3285605"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14435-6_7"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-021-00591-8"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.06.091"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2022.3207429"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2024.3428334"},{"key":"ref16","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017"},{"issue":"1","key":"ref17","first-page":"7234","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref18","first-page":"5887","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Son","year":"2019"},{"key":"ref19","first-page":"10199","article-title":"Weighted QMIX: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Rashid","year":"2020"},{"key":"ref20","first-page":"4405","article-title":"LIIR: Learning individual intrinsic reward in multi-agent reinforcement learning","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Du","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2023.3263013"},{"key":"ref22","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014"},{"key":"ref23","article-title":"RODE: Learning roles to decompose multi-agent tasks","author":"Wang","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2023.3329376"},{"key":"ref25","article-title":"Qatten: A general framework for cooperative multiagent reinforcement learning","author":"Yang","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6211"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3146858"},{"key":"ref29","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","author":"Wang","year":"2020"},{"key":"ref30","first-page":"7611","article-title":"MAVEN: Multi-agent variational exploration","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Mahajan","year":"2019"},{"key":"ref31","article-title":"Rethinking the implementation tricks and monotonicity constraint in cooperative multi-agent reinforcement learning","author":"Hu","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v18i1.21954"},{"key":"ref33","first-page":"2025","article-title":"UPDeT: Universal multi-agent reinforcement learning via policy decoupling with transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1021\/acs.analchem.1c00354"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6221"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105869"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.65109\/LVZZ5205"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11492"},{"issue":"1","key":"ref39","first-page":"331","article-title":"Markov decision processes","volume-title":"Handbooks in Operations Research and Management Science","volume":"2","author":"Puterman","year":"1990"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref41","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3006731"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_22"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43987-2_35"},{"key":"ref46","article-title":"Deep convolutional neural networks with zero-padding: Feature extraction and learning","author":"Han","year":"2023"},{"key":"ref47","article-title":"Action semantics network: Considering the effects of actions in multiagent systems","author":"Wang","year":"2019"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2015.02.024"},{"key":"ref49","article-title":"Fast and accurate deep network learning by exponential linear units (ELUs)","author":"Clevert","year":"2015"},{"key":"ref50","article-title":"StarCraft II: A new challenge for reinforcement learning","author":"Vinyals","year":"2017"}],"container-title":["IEEE Transactions on Computational Social Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570650\/11471691\/11398125.pdf?arnumber=11398125","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T19:55:30Z","timestamp":1775246130000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11398125\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":50,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcss.2025.3628971","relation":{},"ISSN":["2329-924X","2373-7476"],"issn-type":[{"value":"2329-924X","type":"electronic"},{"value":"2373-7476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}