{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:26:49Z","timestamp":1782404809332,"version":"3.54.5"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62276013"],"award-info":[{"award-number":["62276013"]}],"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":["62141605"],"award-info":[{"award-number":["62141605"]}],"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":["62050132"],"award-info":[{"award-number":["62050132"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Natural Science Foundation","award":["1192012"],"award-info":[{"award-number":["1192012"]}]},{"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. Automat. Sci. Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tase.2025.3563725","type":"journal-article","created":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T17:59:17Z","timestamp":1745431157000},"page":"14775-14787","source":"Crossref","is-referenced-by-count":11,"title":["Attention With System Entropy for Optimizing Credit Assignment in Cooperative Multi-Agent Reinforcement Learning"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3747-9484","authenticated-orcid":false,"given":"Wei","family":"Wei","sequence":"first","affiliation":[{"name":"School of Mathematical Sciences, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5555-2477","authenticated-orcid":false,"given":"Haibin","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiyuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Mathematical Sciences, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baifeng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Mathematical Sciences, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7854-7845","authenticated-orcid":false,"given":"Xue","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2020.02.017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3114327"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-11437-3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3168621"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13673"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2022.3164242"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04105-y"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"issue":"1","key":"ref11","first-page":"7234","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":"ref12","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":"ref13","article-title":"Learning to solve the credit assignment problem","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lansdell"},{"key":"ref14","article-title":"Qatten: A general framework for cooperative multiagent reinforcement learning","author":"Yang","year":"2020","journal-title":"arXiv:2002.03939"},{"key":"ref15","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref18","article-title":"CM3: Cooperative multi-goal multi-stage multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09421-1"},{"key":"ref20","first-page":"4403","article-title":"LIIR: Learning individual intrinsic reward in multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Du"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref22","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Iqbal"},{"key":"ref23","first-page":"579","article-title":"AIIR-MIX: Multi-agent reinforcement learning meets attention individual intrinsic reward mixing network","volume-title":"Proc. Asian Conf. Mach. Learn.","author":"Li"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3358894"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108951"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3390\/e22121417"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-021-00815-1"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.7554\/elife.20944.012"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06419-4"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3390\/e23101240"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2020.124925"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2021.111309"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2023.3263013"},{"key":"ref38","first-page":"2186","article-title":"The StarCraft multi-agent challenge","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst. (AAMAS)","author":"Samvelyan"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"issue":"1","key":"ref40","first-page":"7382","article-title":"Curriculum learning for reinforcement learning domains: A framework and survey","volume":"21","author":"Narvekar","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09996-w"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/10839176\/10975045.pdf?arnumber=10975045","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T04:27:13Z","timestamp":1746592033000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10975045\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/tase.2025.3563725","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}