{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:27:05Z","timestamp":1770917225992,"version":"3.50.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002367","name":"Strategic Priority Research Program of Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["XDA27030400"],"award-info":[{"award-number":["XDA27030400"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62293541"],"award-info":[{"award-number":["62293541"]}],"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":["62136008"],"award-info":[{"award-number":["62136008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2018AAA0102404"],"award-info":[{"award-number":["2018AAA0102404"]}]},{"DOI":"10.13039\/501100002367","name":"Youth Innovation Promotion Association of CAS.","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tnnls.2023.3309608","type":"journal-article","created":{"date-parts":[[2023,9,6]],"date-time":"2023-09-06T17:30:12Z","timestamp":1694021412000},"page":"17829-17841","source":"Crossref","is-referenced-by-count":13,"title":["NVIF: Neighboring Variational Information Flow for Cooperative Large-Scale Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7611-064X","authenticated-orcid":false,"given":"Jiajun","family":"Chai","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5384-423X","authenticated-orcid":false,"given":"Yuanheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8218-9633","authenticated-orcid":false,"given":"Dongbin","family":"Zhao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2012.2219061"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2894403"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2935510"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2854300"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2018.2823329"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105869"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2018.8628682"},{"key":"ref8","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":"ref9","first-page":"22069","article-title":"Learning individually inferred communication for multi-agent cooperation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ding"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2011.2174666"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2016.2597763"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121546"},{"key":"ref13","first-page":"1","article-title":"Learning to schedule communication in multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kim"},{"key":"ref14","first-page":"1","article-title":"Learning when to communicate at scale in multiagent cooperative and competitive tasks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Singh"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20868-3_6"},{"key":"ref16","first-page":"964","article-title":"Multi-agent graph-attention communication and teaming","volume-title":"Proc. 20th Int. Conf. Auto. Agents MultiAgent Syst.","author":"Niu"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11244204"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/AGENTS.2019.8929168"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6212"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-022-09580-8"},{"key":"ref21","article-title":"HAMMER: Multi-level coordination of reinforcement learning agents via learned messaging","author":"Gupta","year":"2021","journal-title":"arXiv:2102.00824"},{"key":"ref22","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3071109"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3041469"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3270444"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2020.3022698"},{"key":"ref27","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219993"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6211"},{"key":"ref30","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Foerster"},{"key":"ref31","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Sukhbaatar"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2614002"},{"key":"ref33","first-page":"1","article-title":"Graph convolutional reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Jiang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3243557"},{"key":"ref35","first-page":"1","article-title":"Learning attentional communication for multi-agent cooperation","volume":"31","author":"Jiang","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref36","article-title":"Counterfactual multi-agent reinforcement learning with graph convolution communication","author":"Su","year":"2020","journal-title":"arXiv:2004.00470"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3097947"},{"key":"ref38","first-page":"1020","article-title":"Efficient multi-agent communication via self-supervised information aggregation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Guan"},{"key":"ref39","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref40","article-title":"Is independent learning all you need in the StarCraft multi-agent challenge?","author":"de Witt","year":"2020","journal-title":"arXiv:2011.09533"},{"key":"ref41","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":"ref42","first-page":"26437","article-title":"Coordinated proximal policy optimization","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref43","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"arXiv:1506.02438"},{"key":"ref44","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kipf"},{"key":"ref45","first-page":"1","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","volume-title":"Proc. NIPS Workshop Deep Learn.","author":"Chung"},{"key":"ref46","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Iqbal"},{"key":"ref47","first-page":"1108","article-title":"Modelling the dynamic joint policy of teammates with attention multi-agent DDPG","volume-title":"Proc. 18th Int. Conf. Auto. Agents MultiAgent Syst.","author":"Mao"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10772360\/10242075.pdf?arnumber=10242075","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T19:04:19Z","timestamp":1733252659000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10242075\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":47,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3309608","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}