{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T15:19:10Z","timestamp":1782314350357,"version":"3.54.5"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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":["2022YFA1004702"],"award-info":[{"award-number":["2022YFA1004702"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62173085"],"award-info":[{"award-number":["62173085"]}],"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":["62325304"],"award-info":[{"award-number":["62325304"]}],"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":["U22B2046"],"award-info":[{"award-number":["U22B2046"]}],"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":["62073079"],"award-info":[{"award-number":["62073079"]}],"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":["62088101"],"award-info":[{"award-number":["62088101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangsu Provincial Scientific Research Center of Applied Mathematics","award":["BK20233002"],"award-info":[{"award-number":["BK20233002"]}]},{"name":"Southeast University Interdisciplinary Research Program for Young Scholars"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/tai.2024.3452678","type":"journal-article","created":{"date-parts":[[2024,8,30]],"date-time":"2024-08-30T14:08:13Z","timestamp":1725026893000},"page":"118-131","source":"Crossref","is-referenced-by-count":7,"title":["Policy Consensus-Based Distributed Deterministic Multi-Agent Reinforcement Learning Over Directed Graphs"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0756-6157","authenticated-orcid":false,"given":"Yifan","family":"Hu","sequence":"first","affiliation":[{"name":"School of Mathematics, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1528-8727","authenticated-orcid":false,"given":"Junjie","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Mathematics, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0070-8597","authenticated-orcid":false,"given":"Guanghui","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Mathematics, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9269-334X","authenticated-orcid":false,"given":"Changyin","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2024.3351797"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2023.3262597"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3233592"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982253"},{"key":"ref5","first-page":"456","article-title":"Learning correlated communication topology in multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst. (AAMAS)","author":"Du","year":"2021"},{"key":"ref6","first-page":"4403","article-title":"LIIR: Learning individual intrinsic reward in multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process Syst. (NeurIPS)","author":"Du","year":"2019"},{"key":"ref7","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process Syst. (NeurIPS)","author":"Lowe","year":"2017"},{"key":"ref8","article-title":"Reducing overestimation bias in multi-agent domains using double centralized critics","author":"Ackermann"},{"key":"ref9","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative, multiagent games","volume-title":"Proc. Adv. Neural Inf. Process Syst. (NeurIPS)","author":"Yu","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3329530"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106432"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref13","first-page":"7254","article-title":"Learning attentional communication for multi-agent cooperation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Jiang","year":"2018"},{"key":"ref14","first-page":"5867","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Zhang","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619581"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029969"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3139138"},{"key":"ref18","article-title":"Communication-efficient actor-critic methods for homogeneous Markov games","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Chen","year":"2022"},{"key":"ref19","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Silver","year":"2014"},{"key":"ref20","first-page":"590","article-title":"PIC: Permutation invariant critic for multi-agent deep reinforcement learning","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Liu","year":"2020"},{"key":"ref21","first-page":"1741","article-title":"Learning transferable cooperative behavior in multi-agent team","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst. (AAMAS)","author":"Agarwal","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2012.2209984"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2018.07.020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3094207"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2021.3081996"},{"key":"ref26","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Lillicrap","year":"2016"},{"key":"ref27","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2004.834113"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-93-86279-38-5"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2010.2041686"},{"issue":"1","key":"ref32","first-page":"809","article-title":"Policy evaluation with temporal differences: A survey and comparison","volume":"15","author":"Dann","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref33","first-page":"2085","article-title":"Value-decomposition networks for cooperative multiagent learning based on team reward","volume-title":"Proc. Int. Conf. Auton. Agents MultiAgent Syst. (AAMAS)","author":"Sunehag","year":"2018"},{"key":"ref34","first-page":"12208","article-title":"FACMAC: Factored multi-agent centralised policy gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Peng","year":"2021"},{"key":"ref35","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Fujimoto","year":"2018"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.3001"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9078688\/10841832\/10661302.pdf?arnumber=10661302","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:09:33Z","timestamp":1755911373000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10661302\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":37,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tai.2024.3452678","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}