{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T18:46:01Z","timestamp":1766083561926,"version":"3.48.0"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62222101"],"award-info":[{"award-number":["62222101"]}],"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":["U24A20213"],"award-info":[{"award-number":["U24A20213"]}],"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":["62571011"],"award-info":[{"award-number":["62571011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Natural Science Foundation","award":["L232043"],"award-info":[{"award-number":["L232043"]}]},{"name":"Beijing Natural Science Foundation","award":["L222039"],"award-info":[{"award-number":["L222039"]}]},{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LMS25F010007"],"award-info":[{"award-number":["LMS25F010007"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tsmc.2025.3623649","type":"journal-article","created":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T17:12:53Z","timestamp":1761930773000},"page":"267-278","source":"Crossref","is-referenced-by-count":0,"title":["Role-Policy Enhanced Collaborative Task Learning in Multiagent Systems"],"prefix":"10.1109","volume":"56","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3544-2359","authenticated-orcid":false,"given":"Hang","family":"Fu","sequence":"first","affiliation":[{"name":"School of Cyber Science and Technology, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3170-8952","authenticated-orcid":false,"given":"Jingjing","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ye","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9171-2168","authenticated-orcid":false,"given":"Pengfei","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3189-4222","authenticated-orcid":false,"given":"Jianrui","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5451-7230","authenticated-orcid":false,"given":"Philip","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219993"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref3","first-page":"2186","article-title":"The StarCraft multi-agent challenge","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst. (AAMAS)","author":"Samvelyan"},{"key":"ref4","first-page":"621","article-title":"Towards playing full MOBA games with deep reinforcement learning","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Ye"},{"key":"ref5","first-page":"11881","article-title":"Honor of kings arena: An environment for generalization in competitive reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hua"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2016.2645481"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3063822"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3367005"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2025.3544879"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2021.3126650"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/jsac.2025.3623179"},{"key":"ref12","first-page":"1","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Lowe"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref14","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":"ref15","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Iqbal"},{"key":"ref16","first-page":"9876","article-title":"ROMA: Multi-agent reinforcement learning with eemergent roles","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref17","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":"ref18","first-page":"12979","article-title":"PMIC: Improving multi-agent reinforcement learning with progressive mutual information collaboration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref19","first-page":"1","article-title":"Hierarchical multi-agent skill discovery","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref20","first-page":"1","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Foerster"},{"key":"ref21","first-page":"22069","article-title":"Learning individually inferred communication for multi-agent cooperation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ding"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121546"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-022-09580-8"},{"key":"ref24","first-page":"5711","article-title":"Self-organized group for cooperative multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shao"},{"key":"ref25","first-page":"1","article-title":"RODE: Learning roles to decompose multi-agent tasks","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i10.26390"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/65"},{"key":"ref28","first-page":"1192","article-title":"ACuTE: Automatic curriculum transfer from simple to complex environments","volume-title":"Proc. 21st Int. Conf. Auto. Agents Multiagent Syst.","author":"Shukla"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557611"},{"key":"ref30","first-page":"1","article-title":"Exploration by random network distillation","volume-title":"Proc. 7th Int. Conf. Learn. Represent.","author":"Burda"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428174"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583467"},{"key":"ref33","first-page":"23417","article-title":"Individual reward assisted multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref34","first-page":"9041","article-title":"Policy diagnosis via measuring role diversity in cooperative multi-agent RL","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hu"},{"key":"ref35","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017","journal-title":"arXiv:1706.05296"},{"key":"ref36","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":"ref37","first-page":"1","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","volume-title":"Proc. 9th Int. Conf. Learn. Represent. (ICLR)","author":"Wang"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v24i1.7679"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1142\/S0219525901000188"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17353"},{"key":"ref42","first-page":"727","article-title":"X-means: Extending K-means with efficient estimation of the number of clusters","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pelleg"},{"key":"ref43","first-page":"1","article-title":"HyperNetworks","volume-title":"Proc. 5th Int. Conf. Learn. Represent.","author":"Ha"},{"key":"ref44","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref45","first-page":"28387","article-title":"Individual contributions as intrinsic exploration scaffolds for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref46","first-page":"1679","article-title":"TransfQMix: Transformers for leveraging the graph structure of multi-agent reinforcement learning problems","volume-title":"Proc. Int. Conf. Auto. Agents Multiagent Syst.","author":"Gallici"},{"issue":"318","key":"ref47","first-page":"1","article-title":"Empirical design in reinforcement learning","volume":"25","author":"Patterson","year":"2023","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221021\/11301985\/11223044.pdf?arnumber=11223044","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T18:34:19Z","timestamp":1766082859000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11223044\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":47,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2025.3623649","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"type":"print","value":"2168-2216"},{"type":"electronic","value":"2168-2232"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}