{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:18:37Z","timestamp":1782865117492,"version":"3.54.5"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2021ZD0113303"],"award-info":[{"award-number":["2021ZD0113303"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62192783"],"award-info":[{"award-number":["62192783"]}],"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":["62106100"],"award-info":[{"award-number":["62106100"]}],"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":["62206133"],"award-info":[{"award-number":["62206133"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20221441"],"award-info":[{"award-number":["BK20221441"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Young Elite Scientists Sponsorship Program by CAST","award":["2023QNRC001"],"award-info":[{"award-number":["2023QNRC001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tnnls.2024.3475216","type":"journal-article","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T13:54:18Z","timestamp":1730296458000},"page":"13431-13445","source":"Crossref","is-referenced-by-count":10,"title":["Multi-Task Multi-Agent Reinforcement Learning With Interaction and Task Representations"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5499-4965","authenticated-orcid":false,"given":"Chao","family":"Li","sequence":"first","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8493-1501","authenticated-orcid":false,"given":"Shaokang","family":"Dong","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5379-9539","authenticated-orcid":false,"given":"Shangdong","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujing","family":"Hu","sequence":"additional","affiliation":[{"name":"NetEase Fuxi AI Lab, NetEase Inc., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8445-4330","authenticated-orcid":false,"given":"Tianyu","family":"Ding","sequence":"additional","affiliation":[{"name":"Applied Sciences Group, Microsoft Corporation, Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0935-7124","authenticated-orcid":false,"given":"Wenbin","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2488-1813","authenticated-orcid":false,"given":"Yang","family":"Gao","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2012.2219061"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3089834"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAR49639.2020.9107997"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3070484"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3070584"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1912341117"},{"key":"ref7","first-page":"2681","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Omidshafiei"},{"key":"ref8","first-page":"4499","article-title":"Distral: Robust multitask reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Teh"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6221"},{"key":"ref10","article-title":"Evolutionary population curriculum for scaling multi-agent reinforcement learning","author":"Long","year":"2020","journal-title":"arXiv:2003.10423"},{"key":"ref11","article-title":"UPDeT: Universal multi-agent reinforcement learning via policy decoupling with transformers","author":"Hu","year":"2021","journal-title":"arXiv:2101.08001"},{"key":"ref12","first-page":"4596","article-title":"Randomized entity-wise factorization for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Iqbal"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1515\/9781400881970-018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.2200\/S00355ED1V01Y201107AIM016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11492"},{"key":"ref18","first-page":"2186","article-title":"The starcraft multi-agent challenge","volume-title":"Proc. 18th Int. Conf. Auto. Agents MultiAgent Syst.","author":"Samvelyan"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref20","first-page":"1989","article-title":"Scaling multi-agent reinforcement learning with selective parameter sharing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Christianos"},{"key":"ref21","first-page":"10707","article-title":"Shared experience actor-critic for multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Christianos"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967849"},{"key":"ref23","first-page":"1","article-title":"An efficient transfer learning framework for multiagent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3034424"},{"issue":"7","key":"ref25","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"Taylor","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref26","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. 31st Conf. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref28","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yu"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.23860\/diss-li-hepfeng-2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2996209"},{"key":"ref31","first-page":"16509","article-title":"Multi-agent reinforcement learning is a sequence modeling problem","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wen"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref33","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. 17th Int. Conf. Auto. Agents MultiAgent Syst.","author":"Sunehag"},{"key":"ref34","first-page":"4295","article-title":"QMix: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rashid"},{"key":"ref35","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"},{"key":"ref36","first-page":"1","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3089493"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6220"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3070203"},{"key":"ref40","first-page":"9876","article-title":"ROMA: Multi-agent reinforcement learning with emergent roles","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Wang"},{"key":"ref41","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11073756\/10738426.pdf?arnumber=10738426","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T17:48:39Z","timestamp":1752169719000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10738426\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":41,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3475216","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}