{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T21:09:40Z","timestamp":1774300180024,"version":"3.50.1"},"reference-count":52,"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":[{"name":"National Key Research and Development Program of China","award":["2022YFA1004600"],"award-info":[{"award-number":["2022YFA1004600"]}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62125304"],"award-info":[{"award-number":["62125304"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","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\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62073182"],"award-info":[{"award-number":["62073182"]}],"id":[{"id":"10.13039\/501100001809","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.2024.3369592","type":"journal-article","created":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T14:06:10Z","timestamp":1709215570000},"page":"1684-1696","source":"Crossref","is-referenced-by-count":14,"title":["Multi-Agent Reinforcement Learning With Decentralized Distribution Correction"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4562-3901","authenticated-orcid":false,"given":"Kuo","family":"Li","sequence":"first","affiliation":[{"name":"Department of Automation, Center for Intelligent and Networked Systems (CFINS), Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4683-7215","authenticated-orcid":false,"given":"Qing-Shan","family":"Jia","sequence":"additional","affiliation":[{"name":"Department of Automation, Center for Intelligent and Networked Systems (CFINS), Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref6","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3114327"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2018.2877499"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3156384"},{"key":"ref12","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017","journal-title":"arXiv:1706.05296"},{"key":"ref13","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":"ref14","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref15","first-page":"5527","article-title":"Independent policy gradient methods for competitive reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Daskalakis"},{"key":"ref16","first-page":"4259","article-title":"Last-iterate convergence of decentralized optimistic gradient descent\/ascent in infinite-horizon competitive Markov games","volume-title":"Proc. Conf. Learn. Theory","author":"Wei"},{"key":"ref17","first-page":"11602","article-title":"Policy optimization provably converges to nash equilibria in zero-sum linear quadratic games","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"32","author":"Zhang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref20","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":"ref21","article-title":"Reducing overestimation bias in multi-agent domains using double centralized critics","author":"Ackermann","year":"2019","journal-title":"arXiv:1910.01465"},{"key":"ref22","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lillicrap"},{"key":"ref23","first-page":"12208","article-title":"FACMAC: Factored multi-agent centralised policy gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Peng"},{"key":"ref24","first-page":"980","article-title":"Deep coordination graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"B\u00f6hmer"},{"key":"ref25","first-page":"1","article-title":"Context-aware sparse deep coordination graphs","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-94662-3_12"},{"key":"ref27","first-page":"7613","article-title":"MAVEN: Multi-agent variational exploration","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"32","author":"Mahajan"},{"key":"ref28","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":"ref29","article-title":"Experience augmentation: Boosting and accelerating off-policy multi-agent reinforcement learning","author":"Ye","year":"2020","journal-title":"arXiv:2005.09453"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CAC57257.2022.10055893"},{"key":"ref31","first-page":"1","article-title":"Boosting multiagent reinforcement learning via permutation invariant and permutation equivariant networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Jianye"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3100709"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CAC51589.2020.9327245"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2021.109872"},{"key":"ref35","first-page":"1184","article-title":"Value propagation for decentralized networked deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"320","author":"Qu"},{"key":"ref36","first-page":"1626","article-title":"Finite-time analysis of distributed TD (0) with linear function approximation on multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Doan"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683356"},{"key":"ref38","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":"ref39","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref40","first-page":"1","article-title":"Convergence of Q-learning: A simple proof","author":"Melo","year":"2001"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.6.1185"},{"key":"ref42","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref43","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.35.11.1367"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1127777.1127806"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IPSN.2005.1440896"},{"key":"ref47","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-023-3872-9"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tase.2023.3282257"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3207871"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2023.3281935"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3078445"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8856\/10839176\/10456565.pdf?arnumber=10456565","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T20:12:28Z","timestamp":1774296748000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10456565\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/tase.2024.3369592","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}