{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T20:10:39Z","timestamp":1788811839294,"version":"build-2803163510"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Innovation and Technology Commission-Mainland-Hong Kong Joint Funding Scheme","award":["MHP\/038\/23"],"award-info":[{"award-number":["MHP\/038\/23"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62376048"],"award-info":[{"award-number":["62376048"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1109\/tnnls.2026.3658520","type":"journal-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T20:53:10Z","timestamp":1772571190000},"page":"4035-4049","source":"Crossref","is-referenced-by-count":1,"title":["Rethinking the Utilization of Individual Rewards in Multiagent Reinforcement Learning With Sparse Team Rewards"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4658-565X","authenticated-orcid":false,"given":"Yang","family":"Zhang","sequence":"first","affiliation":[{"name":"The Hong Kong Polytechnic University","place":["Hong Kong, China"],"department":["Department of Electrical and Electronic Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0110-8032","authenticated-orcid":false,"given":"Yunjian","family":"Xu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong (CUHK)","place":["Hong Kong, China"],"department":["Department of Mechanical and Automation Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9157-6050","authenticated-orcid":false,"given":"Chengwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Dalian Maritime University","place":["Dalian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7635-5022","authenticated-orcid":false,"given":"Zhihe","family":"Yang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong (CUHK)","place":["Hong Kong, China"],"department":["Department of Mechanical and Automation Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Tang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6969-7764","authenticated-orcid":false,"given":"Edward","family":"Chung","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University","place":["Hong Kong, China"],"department":["Department of Electrical and Electronic Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2020.2999890"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29681"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3125918"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103122"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341303"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.65109\/LVZZ5205"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1787"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5878"},{"key":"ref10","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":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3142822"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3134702"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2007.08.009"},{"key":"ref14","first-page":"1479","article-title":"Unifying count-based exploration and intrinsic motivation","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","volume":"29","author":"Bellemare"},{"key":"ref15","first-page":"21937","article-title":"Lazy agents: A new perspective on solving sparse reward problem in multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Liu"},{"key":"ref16","first-page":"10041","article-title":"MASER: Multi-agent reinforcement learning with subgoals generated from experience replay buffer","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Jeon"},{"key":"ref17","first-page":"6826","article-title":"Cooperative exploration for multi-agent deep reinforcement learning","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/32"},{"key":"ref19","first-page":"3991","article-title":"Celebrating diversity in shared multi-agent reinforcement learning","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/37"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110884"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759651"},{"key":"ref23","first-page":"23417","article-title":"Individual reward assisted multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Wang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/65"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11396"},{"key":"ref26","first-page":"6651","article-title":"Evolutionary reinforcement learning for sample-efficient multiagent coordination","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"119","author":"Majumdar"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i13.33566"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0361"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.65109\/lvzz5205"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340876"},{"key":"ref31","article-title":"Centralized model and exploration policy for multi-agent RL","author":"Zhang","year":"2021","journal-title":"arXiv:2107.06434"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.65109\/bjtx8963"},{"key":"ref33","article-title":"Influence-based multi-agent exploration","author":"Wang","year":"2019","journal-title":"arXiv:1910.05512"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650769"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3281"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i10.26384"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2024.3401649"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3390\/make1010002"},{"key":"ref39","first-page":"1","article-title":"Exploration by random network distillation","volume-title":"Proc. 7th Int. Conf. Learn. Represent.","author":"Burda"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428174"},{"key":"ref41","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":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191420"},{"key":"ref43","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","volume-title":"Proc. 19th Int. Conf. Mach. Learn.","author":"Kakade"},{"key":"ref44","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref45","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Schulman"},{"issue":"178","key":"ref46","first-page":"1","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":"ref47","first-page":"7611","article-title":"MAVEN: Multi-agent variational exploration","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","volume":"32","author":"Mahajan"},{"key":"ref48","first-page":"1","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3183865"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3172572"},{"key":"ref51","first-page":"4403","article-title":"LIIR: Learning individual intrinsic reward in multi-agent reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","volume":"32","author":"Du"},{"key":"ref52","article-title":"Convex analysis: (PMS-28)","author":"Rockafellar","year":"2015"},{"key":"ref53","volume-title":"Real Analysis: Modern Techniques and Their Applications","author":"Folland","year":"1999"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/BF00353877"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11676227\/11419180.pdf?arnumber=11419180","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T19:20:27Z","timestamp":1788808827000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11419180\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":54,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2026.3658520","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]}}}