{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:08:10Z","timestamp":1784736490037,"version":"3.55.0"},"reference-count":46,"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":["62088101"],"award-info":[{"award-number":["62088101"]}],"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"}]},{"name":"General Joint Fund of the Equipment Advance Research Program of Ministry of Education","award":["8091B022114"],"award-info":[{"award-number":["8091B022114"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/tnnls.2023.3329530","type":"journal-article","created":{"date-parts":[[2023,11,10]],"date-time":"2023-11-10T14:02:51Z","timestamp":1699624971000},"page":"665-676","source":"Crossref","is-referenced-by-count":37,"title":["Graph Soft Actor\u2013Critic Reinforcement Learning for Large-Scale Distributed Multirobot Coordination"],"prefix":"10.1109","volume":"36","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"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2021.3081996"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635898"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3146912"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2961753"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2012.2219061"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2984944"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3095431"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3104987"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3000264"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.06.024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2015.2465071"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref13","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812263"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3172168"},{"key":"ref17","first-page":"25817","article-title":"Scalable multi-agent reinforcement learning through intelligent information aggregation","volume-title":"Proc. 40th Int. Conf. Mach. Learn. (ICML)","author":"Nayak"},{"key":"ref18","article-title":"A survey of multi-agent reinforcement learning with communication","author":"Zhu","year":"2022","journal-title":"arXiv:2203.08975"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.3016143"},{"key":"ref20","first-page":"1","article-title":"Graph convolutional reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Jiang"},{"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"},{"key":"ref22","first-page":"823","article-title":"Graph policy gradients for large scale robot control","volume-title":"Proc. 3rd Conf. Robot Learn. (CoRL)","author":"Khan"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3074885"},{"key":"ref24","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning","volume-title":"Proc. Int. Conf. Auton. Agents MultiAgent Syst. (AAMAS)","author":"Sunehag"},{"key":"ref25","first-page":"4295","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","author":"Rashid"},{"key":"ref26","first-page":"1","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wang"},{"key":"ref27","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref28","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"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref30","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn. (ICML)","author":"Iqbal"},{"key":"ref31","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Lillicrap"},{"key":"ref32","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Sukhbaatar"},{"key":"ref33","article-title":"Multiagent bidirectionally-coordinated nets: Emergence of human-level coordination in learning to play StarCraft combat games","author":"Peng","year":"2017","journal-title":"arXiv:1703.10069"},{"key":"ref34","first-page":"7254","article-title":"Learning attentional communication for multi-agent cooperation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Jiang"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref36","article-title":"Graph convolutional value decomposition in multi-agent reinforcement learning","author":"Naderializadeh","year":"2020","journal-title":"arXiv:2010.04740"},{"key":"ref37","first-page":"590","article-title":"PIC: Permutation invariant critic for multi-agent deep reinforcement learning","volume-title":"Proc. 3rd Conf. Robot Learn. (CoRL)","author":"Liu"},{"key":"ref38","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","author":"Haarnoja"},{"key":"ref39","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635836"},{"key":"ref41","first-page":"834","article-title":"Improving stochastic policy gradients in continuous control with deep reinforcement learning using the beta distribution","volume-title":"Proc. 34th Int. Conf. Mach. Learn. (ICML)","author":"Chou"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2004.834113"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461113"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593871"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811744"},{"key":"ref46","article-title":"Distillation strategies for proximal policy optimization","author":"Green","year":"2019","journal-title":"arXiv:1901.08128"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10832116\/10314538.pdf?arnumber=10314538","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:39:05Z","timestamp":1764959945000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10314538\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":46,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3329530","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}