{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T23:12:58Z","timestamp":1771024378169,"version":"3.50.1"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"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":["62125304"],"award-info":[{"award-number":["62125304"]}],"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62073182"],"award-info":[{"award-number":["62073182"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2022YFA1004600"],"award-info":[{"award-number":["2022YFA1004600"]}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L233005"],"award-info":[{"award-number":["L233005"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"name":"BNRist","award":["BNR2024TD03003"],"award-info":[{"award-number":["BNR2024TD03003"]}]},{"name":"111 International Collaboration","award":["B25027"],"award-info":[{"award-number":["B25027"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tac.2025.3534639","type":"journal-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:52:44Z","timestamp":1738003964000},"page":"4217-4224","source":"Crossref","is-referenced-by-count":1,"title":["Multiagent Reinforcement Learning for Constrained Markov Decision Processes by Consensus-Based Primal\u2013Dual Method"],"prefix":"10.1109","volume":"70","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3423-3792","authenticated-orcid":false,"given":"Gaochen","family":"Cui","sequence":"first","affiliation":[{"name":"CFINS, Department of Automations, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4683-7215","authenticated-orcid":false,"given":"Qing-Shan","family":"Jia","sequence":"additional","affiliation":[{"name":"CFINS, Department of Automations, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8826-0362","authenticated-orcid":false,"given":"Xiaohong","family":"Guan","sequence":"additional","affiliation":[{"name":"CFINS, Department of Automations, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2801880"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2018.2850023"},{"key":"ref3","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2659727"},{"key":"ref8","first-page":"6382","article-title":"Multi-agent actorcritic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2017.2672750"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2017.2760863"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2004.08.007"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2010.08.013"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17062"},{"key":"ref14","first-page":"179","article-title":"Off-policy actorcritic","volume-title":"Proc. 29th Int. Conf. Mach. Learn.","volume":"1","author":"Degris","year":"2012"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref16","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","year":"2018"},{"key":"ref17","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2018"},{"key":"ref18","first-page":"256","article-title":"Scalable reinforcement learning of localized policies for multi-agent networked systems","volume-title":"Proc. Learn. Dyn. Control","author":"Qu","year":"2020"},{"key":"ref19","first-page":"2074","article-title":"Scalable multi-agent reinforcement learning for networked systems with average reward","volume":"33","author":"Qu","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2007.902736"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref22","first-page":"7555","article-title":"Constrained reinforcement learning has zero duality gap","volume":"32","author":"Paternain","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2650563"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1137\/16M1084316"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TSIPN.2018.2866342"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2564339"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4899-2696-8","volume-title":"Stochastic Approximation Algorithms and Applications. Stochastic Approximation Algorithms and Applications","author":"Kushner","year":"1997"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-0805-2_11"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1137\/S036301299731669X"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s12045-013-0136-x"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9\/11018158\/10854570.pdf?arnumber=10854570","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,2]],"date-time":"2025-06-02T15:50:20Z","timestamp":1748879420000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10854570\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":30,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tac.2025.3534639","relation":{},"ISSN":["0018-9286","1558-2523","2334-3303"],"issn-type":[{"value":"0018-9286","type":"print"},{"value":"1558-2523","type":"electronic"},{"value":"2334-3303","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}