{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T08:42:02Z","timestamp":1773736922283,"version":"3.50.1"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"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":["U1813216"],"award-info":[{"award-number":["U1813216"]}],"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":["62192751"],"award-info":[{"award-number":["62192751"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Project of China","doi-asserted-by":"publisher","award":["2017YFC0704100"],"award-info":[{"award-number":["2017YFC0704100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Project of China","doi-asserted-by":"publisher","award":["2016YFB0901900"],"award-info":[{"award-number":["2016YFB0901900"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"111 International Collaboration Program of China","award":["BP2018006"],"award-info":[{"award-number":["BP2018006"]}]},{"name":"BNRist Program","award":["BNR2019TD01009"],"award-info":[{"award-number":["BNR2019TD01009"]}]},{"name":"STI 2030\u2014Major Projects","award":["2022ZD0208804"],"award-info":[{"award-number":["2022ZD0208804"]}]},{"name":"National Innovation Center of High Speed Train Research and Development Project","award":["CX\/KJ-2020-0006"],"award-info":[{"award-number":["CX\/KJ-2020-0006"]}]},{"name":"InnoHK Initiative, The Government of HKSAR"},{"name":"Laboratory for AI-Powered Financial Technologies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/tnnls.2023.3326744","type":"journal-article","created":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T14:12:02Z","timestamp":1699366322000},"page":"2051-2065","source":"Crossref","is-referenced-by-count":3,"title":["Celebrating Diversity With Subtask Specialization in Shared Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6650-9673","authenticated-orcid":false,"given":"Chenghao","family":"Li","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"given":"Tonghan","family":"Wang","sequence":"additional","affiliation":[{"name":"Harvard University, Boston, MA, USA"}]},{"given":"Chengjie","family":"Wu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"given":"Qianchuan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"given":"Jun","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8068-0162","authenticated-orcid":false,"given":"Chongjie","family":"Zhang","sequence":"additional","affiliation":[{"name":"Washington University in St. Louis, St. Louis, MO, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v25i1.7886"},{"key":"ref2","first-page":"1278","article-title":"Hierarchical multiagent reinforcement learning for maritime traffic management","volume-title":"Proc. 19th Int. Conf. Auto. Agents MultiAgent Syst.","author":"Singh"},{"key":"ref3","article-title":"Guided deep reinforcement learning for swarm systems","author":"H\u00fcttenrauch","year":"2017","journal-title":"arXiv:1709.06011"},{"key":"ref4","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":"ref5","first-page":"4292","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Int. Conf. Mach. Learn.","author":"Rashid"},{"key":"ref6","first-page":"1","article-title":"Qplex: Duplex dueling multi-agent Q-learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wang"},{"key":"ref7","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref8","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":"ref9","article-title":"QTRAN++: Improved value transformation for cooperative multi-agent reinforcement learning","author":"Son","year":"2020","journal-title":"arXiv:2006.12010"},{"key":"ref10","first-page":"853","article-title":"Modeling the interaction between agents in cooperative multi-agent reinforcement learning","volume-title":"Proc. 20th Int. Conf. Auto. Agents MultiAgent Syst.","author":"Ma"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref12","article-title":"The StarCraft multi-agent challenge","author":"Samvelyan","year":"2019","journal-title":"arXiv:1902.04043"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5878"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref15","article-title":"Reinforcement learning with competitive ensembles of information-constrained primitives","author":"Goyal","year":"2019","journal-title":"arXiv:1906.10667"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1561\/9781601981851"},{"key":"ref17","first-page":"1","article-title":"Dynamics-aware unsupervised discovery of skills","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Sharma"},{"key":"ref18","first-page":"1","article-title":"Influence-based multi-agent exploration","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wang"},{"key":"ref19","first-page":"1","article-title":"Probabilistic recursive reasoning for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wen"},{"key":"ref20","first-page":"1","article-title":"DOP: Off-policy multi-agent decomposed policy gradients","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wang"},{"key":"ref21","article-title":"Is independent learning all you need in the StarCraft multi-agent challenge?","author":"de Witt","year":"2020","journal-title":"arXiv:2011.09533"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2103.01955"},{"key":"ref23","first-page":"1","article-title":"Weighted QMIX: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Rashid"},{"key":"ref24","first-page":"1523","article-title":"Multiagent planning with factored MDPS","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Guestrin"},{"key":"ref25","first-page":"227","article-title":"Coordinated reinforcement learning","volume-title":"Proc. ICML","volume":"2","author":"Guestrin"},{"key":"ref26","first-page":"1","article-title":"Deep coordination graphs","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"B\u00f6hmer"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3152251"},{"key":"ref28","first-page":"1","article-title":"Learning nearly decomposable value functions with communication minimization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wang"},{"key":"ref29","first-page":"1","article-title":"Learning when to communicate at scale in multiagent cooperative and competitive tasks","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Singh"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6212"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121546"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022140919877"},{"key":"ref34","first-page":"1","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Kulkarni"},{"key":"ref35","first-page":"1","article-title":"Hindsight experience replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Andrychowicz"},{"key":"ref36","first-page":"1","article-title":"Planning with goal-conditioned policies","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Nasiriany"},{"key":"ref37","first-page":"1","article-title":"Learning subgoal representations with slow dynamics","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref38","first-page":"1430","article-title":"Goal-conditioned reinforcement learning with imagined subgoals","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chane-Sane"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11740"},{"key":"ref40","first-page":"1","article-title":"DAC: The double actor-critic architecture for learning options","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Zhang"},{"key":"ref41","article-title":"SOAC: The soft option actor-critic architecture","author":"Li","year":"2020","journal-title":"arXiv:2006.14363"},{"key":"ref42","article-title":"Hierarchical reinforcement learning by discovering intrinsic options","author":"Zhang","year":"2021","journal-title":"arXiv:2101.06521"},{"key":"ref43","article-title":"Hierarchical cooperative multi-agent reinforcement learning with skill discovery","author":"Yang","year":"2019","journal-title":"arXiv:1912.03558"},{"key":"ref44","first-page":"1","article-title":"Rode: Learning roles to decompose multi-agent tasks","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wang"},{"key":"ref45","first-page":"1","article-title":"ROMA: Multi-agent reinforcement learning with emergent roles","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref47","article-title":"Exploration by random network distillation","author":"Burda","year":"2018","journal-title":"arXiv:1810.12894"},{"key":"ref48","article-title":"Never give up: Learning directed exploration strategies","author":"Badia","year":"2020","journal-title":"arXiv:2002.06038"},{"key":"ref49","first-page":"507","article-title":"Agent57: Outperforming the Atari human benchmark","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Badia"},{"key":"ref50","first-page":"1","article-title":"Diversity is all you need: Learning skills without a reward function","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Eysenbach"},{"key":"ref51","first-page":"1317","article-title":"Explore, discover and learn: Unsupervised discovery of state-covering skills","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Campos"},{"key":"ref52","first-page":"7611","article-title":"MAVEN: Multi-agent variational exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mahajan"},{"key":"ref53","article-title":"The emergence of individuality in multi-agent reinforcement learning","author":"Jiang","year":"2020","journal-title":"arXiv:2006.05842"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref55","first-page":"2324","article-title":"A Q-values sharing framework for multiple independent q-learners","volume-title":"Proc. 18th Int. Conf. Auto. Agents MultiAgent Syst.","author":"Zhu"},{"key":"ref56","article-title":"Auto-Agent-distiller: Towards efficient deep reinforcement learning agents via neural architecture search","author":"Fu","year":"2020","journal-title":"arXiv:2012.13091"},{"key":"ref57","first-page":"1","article-title":"Shared experience actor-critic for multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Christianos"},{"key":"ref58","first-page":"1","article-title":"Promoting coordination through policy regularization in multi-agent deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Roy"},{"key":"ref59","article-title":"Scaling multi-agent reinforcement learning with selective parameter sharing","author":"Christianos","year":"2021","journal-title":"arXiv:2102.07475"},{"key":"ref60","first-page":"1","article-title":"Celebrating diversity in shared multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10877690\/10310295.pdf?arnumber=10310295","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:39:18Z","timestamp":1764959958000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10310295\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":60,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3326744","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}