{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:34:28Z","timestamp":1777653268301,"version":"3.51.4"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tkde.2026.3658366","type":"journal-article","created":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T20:30:33Z","timestamp":1769545833000},"page":"2209-2220","source":"Crossref","is-referenced-by-count":3,"title":["Communication Learning in Multi-Agent Systems From Graph Modeling Perspective"],"prefix":"10.1109","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6860-2222","authenticated-orcid":false,"given":"Shengchao","family":"Hu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1459-3250","authenticated-orcid":false,"given":"Ziqing","family":"Fan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5659-3464","authenticated-orcid":false,"given":"Li","family":"Shen","sequence":"additional","affiliation":[{"name":"Shenzhen Campus of Sun Yat-sen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5390-9053","authenticated-orcid":false,"given":"Ya","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"SMARTS: Scalable multi-agent reinforcement learning training school for autonomous driving","author":"Zhou","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_31"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313433"},{"key":"ref4","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref5","article-title":"Multiagent bidirectionally-coordinated nets: Emergence of human-level coordination in learning to play StarCraft combat games","author":"Peng","year":"2017"},{"key":"ref6","article-title":"MALib: A parallel framework for population-based multi-agent reinforcement learning","volume":"24","author":"Zhou","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref7","first-page":"4193","article-title":"A unified game-theoretic approach to multiagent reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lanctot"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.55417\/fr.2022032"},{"key":"ref9","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref10","first-page":"6860","article-title":"Coach-player multi-agent reinforcement learning for dynamic team composition","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref11","article-title":"Learning to schedule communication in multi-agent reinforcement learning","author":"Kim","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref13","article-title":"Trust region policy optimisation in multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kuba"},{"key":"ref14","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sukhbaatar"},{"key":"ref15","first-page":"1538","article-title":"TarMAC: Targeted multi-agent communication","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Das"},{"key":"ref16","article-title":"ToM2C: Target-oriented multi-agent communication and cooperation with theory of mind","author":"Wang","year":"2021"},{"key":"ref17","first-page":"7265","article-title":"Learning attentional communication for multi-agent cooperation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Jiang"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1109\/TKDE.2026.3658366","article-title":"Learning multi-agent communication from graph modeling perspective","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Hu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_179433"},{"key":"ref20","article-title":"Relational forward models for multi-agent learning","author":"Tacchetti","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6212"},{"key":"ref22","first-page":"16509","article-title":"Multi-agent reinforcement learning is a sequence modeling problem","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wen"},{"key":"ref23","article-title":"An overview of multi-agent reinforcement learning from game theoretical perspective","author":"Yang","year":"2020"},{"key":"ref24","first-page":"746","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","volume-title":"Proc. 15th Nat. Conf. Artif. Intell. 10th Innov. Appl. Artif. Intell. Conf.","author":"Claus"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.65109\/hgwa8807"},{"key":"ref27","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref28","first-page":"5887","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Son"},{"key":"ref29","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017"},{"key":"ref30","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.65109\/LVZZ5205"},{"key":"ref32","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Foerster"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6211"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.65109\/yhuo7761"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.65109\/SLOB2372"},{"key":"ref36","article-title":"Learning when to communicate at scale in multiagent cooperative and competitive tasks","author":"Singh","year":"2018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5957"},{"key":"ref38","first-page":"22069","article-title":"Learning individually inferred communication for multi-agent cooperation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ding"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/82"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-022-06286-6"},{"issue":"44","key":"ref41","article-title":"Temporal dynamic weighted graph convolution for multi-agent reinforcement learning","volume-title":"Proc. Annu. Meeting Cogn. Sci. Soc.","volume":"44","author":"Liu"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3408271"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4353-9"},{"key":"ref44","first-page":"19182","article-title":"HarmoDT: Harmony multi-task decision transformer for offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hu"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6243"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref47","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref48","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/BF02098169"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-007-0176-2"},{"key":"ref51","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2016"},{"key":"ref52","article-title":"The concrete distribution: A continuous relaxation of discrete random variables","author":"Maddison","year":"2016"},{"key":"ref53","first-page":"27287","article-title":"Probabilistic bilevel coreset selection","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhou"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-014-0846-1"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.65109\/vjxc6483"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5878"},{"key":"ref57","article-title":"UPDeT: Universal multi-agent reinforcement learning via policy decoupling with transformers","author":"Hu","year":"2021"},{"key":"ref58","article-title":"Learning nearly decomposable value functions via communication minimization","author":"Wang","year":"2019"},{"key":"ref59","article-title":"QGNN: Value function factorisation with graph neural networks","author":"Kortvelesy","year":"2022"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/11427039\/11365584.pdf?arnumber=11365584","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T05:22:08Z","timestamp":1773120128000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11365584\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":59,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2026.3658366","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}