{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T15:40:51Z","timestamp":1787154051509,"version":"build-2736575974"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306062"],"award-info":[{"award-number":["62306062"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306063"],"award-info":[{"award-number":["62306063"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62576078"],"award-info":[{"award-number":["62576078"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018542","name":"Natural Science Foundation of Sichuan Province","doi-asserted-by":"publisher","award":["2024NSFSC1469"],"award-info":[{"award-number":["2024NSFSC1469"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tcyb.2025.3645464","type":"journal-article","created":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T18:31:35Z","timestamp":1766514695000},"page":"2374-2387","source":"Crossref","is-referenced-by-count":2,"title":["Dual-Policy Fusion for Multitask Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"56","author":[{"given":"Yandong","family":"Chen","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naizhuo","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9257-126X","authenticated-orcid":false,"given":"Mingsheng","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7590-144X","authenticated-orcid":false,"given":"Liwei","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6114-3441","authenticated-orcid":false,"given":"Hong","family":"Qu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5867-9322","authenticated-orcid":false,"given":"Zhang","family":"Yi","sequence":"additional","affiliation":[{"name":"College of Computer Science, Sichuan University, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref2","article-title":"Multi-agent reinforcement learning for autonomous driving: A survey","author":"Zhang","year":"2024","journal-title":"arXiv:2408.09675"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/s23073625"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/s23052373"},{"key":"ref5","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017","journal-title":"arXiv:1706.05296"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2447"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref8","first-page":"4292","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rashid"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2025.3557694"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2024.3453892"},{"key":"ref11","article-title":"Discovering generalizable multi-agent coordination skills from multi-task offline data","volume-title":"Proc. The 11th Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-023-3862-1"},{"key":"ref13","article-title":"UPDeT: Universal multi-agent reinforcement learning via policy decoupling with transformers","author":"Hu","year":"2021","journal-title":"arXiv:2101.08001"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3540758"},{"key":"ref15","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yu"},{"key":"ref16","article-title":"Conflict-averse gradient aggregation for constrained multi-objective reinforcement learning","author":"Kim","year":"2024","journal-title":"arXiv:2403.00282"},{"issue":"32","key":"ref17","first-page":"1","article-title":"Heterogeneous-agent reinforcement learning","volume":"25","author":"Zhong","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref18","article-title":"Reinforcement learning with deep energy-based policies","author":"Haarnoja","year":"2017","journal-title":"arXiv:1702.08165"},{"key":"ref19","article-title":"The StarCraft multi-agent challenge","author":"Samvelyan","year":"2019","journal-title":"arXiv:1902.04043"},{"key":"ref20","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lowe"},{"key":"ref21","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative, multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref22","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","author":"Wang","year":"2020","journal-title":"arXiv:2008.01062"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i18.34099"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i22.34500"},{"key":"ref25","article-title":"Sharing knowledge in multi-task deep reinforcement learning","author":"D\u2019Eramo","year":"2024","journal-title":"arXiv:2401.09561"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3747"},{"key":"ref27","first-page":"36507","article-title":"Contrastive modules with temporal attention for multi-task reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lan"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3271445"},{"key":"ref29","article-title":"One subgoal at a time: Zero-shot generalization to arbitrary linear temporal logic requirements in multi-task reinforcement learning","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Guo"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25825"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-025-01816-w"},{"key":"ref32","first-page":"1","article-title":"Distral: Robust multitask reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Teh"},{"key":"ref33","article-title":"Cooperative multi-agent transfer learning with level-adaptive credit assignment","author":"Zhou","year":"2021","journal-title":"arXiv:2106.00517"},{"key":"ref34","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"arXiv:1706.03762"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3475216"},{"key":"ref36","article-title":"Bi-level knowledge transfer for multi-task multi-agent reinforcement learning","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref37","article-title":"Revisiting parameter sharing in multi-agent deep reinforcement learning","author":"Terry","year":"2020","journal-title":"arXiv:2005.13625"},{"key":"ref38","article-title":"Multi-task multi-agent shared layers are universal cognition of multi-agent coordination","author":"Wang","year":"2023","journal-title":"arXiv:2312.15674"},{"key":"ref39","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref40","article-title":"Qatten: A general framework for cooperative multiagent reinforcement learning","author":"Yang","year":"2020","journal-title":"arXiv:2002.03939"},{"key":"ref41","first-page":"1365","article-title":"Regularized softmax deep multi-agent Q-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pan"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.107035"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221036\/11442719\/11313317.pdf?arnumber=11313317","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T04:47:14Z","timestamp":1773895634000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11313317\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":42,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2025.3645464","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}