{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T09:15:07Z","timestamp":1773911707431,"version":"3.50.1"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Beijing Natural Science Foundation Haidian Original Innovation Joint","award":["L232035"],"award-info":[{"award-number":["L232035"]}]},{"name":"Beijing Natural Science Foundation Haidian Original Innovation Joint","award":["L222154"],"award-info":[{"award-number":["L222154"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tg.2025.3629681","type":"journal-article","created":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:46:21Z","timestamp":1763059581000},"page":"151-162","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Graph Coordination Strategy in Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"18","author":[{"given":"Zhongwei","family":"Yu","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4857-9053","authenticated-orcid":false,"given":"Jingqing","family":"Ruan","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8251-9118","authenticated-orcid":false,"given":"Dengpeng","family":"Xing","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Lowe","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357902"},{"key":"ref3","first-page":"2576","article-title":"Grid-wise control for multi-agent reinforcement learning in video game AI","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Du","year":"2019"},{"key":"ref4","first-page":"7265","article-title":"Learning attentional communication for multi-agent cooperation","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Jiang","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6211"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.65109\/yhuo7761"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.65109\/fxam2191"},{"key":"ref8","first-page":"980","article-title":"Deep coordination graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bohmer","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.65109\/czoy2835"},{"key":"ref10","first-page":"1","article-title":"Context-aware sparse deep coordination graphs","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6226"},{"key":"ref12","article-title":"Multiagent rollout algorithms and reinforcement learning","author":"Bertsekas","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1003814"},{"key":"ref14","article-title":"Probabilistic Graphical Models: Principles and Techniques","volume-title":"Adaptive Computation and Machine Learning","author":"Koller","year":"2009"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.65109\/rvse8744"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.3030571"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.65109\/JSRC7365"},{"key":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v18i1.21954"},{"key":"ref20","first-page":"20580","article-title":"Divergence-regularized multi-agent actor-critic","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Su","year":"2022"},{"key":"ref21","article-title":"Off-policy actor-critic","author":"Degris","year":"2012"},{"key":"ref22","first-page":"3040","article-title":"Social influence as intrinsic motivation for multi-agent deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jaques","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126974"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112665"},{"key":"ref25","article-title":"Graph convolutional reinforcement learning","author":"Jiang","year":"2018"},{"key":"ref26","first-page":"7154","article-title":"DAG-GNN: DAG structure learning with graph neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu","year":"2019"},{"key":"ref27","first-page":"1","article-title":"Causal discovery with reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2019"},{"key":"ref28","first-page":"195","article-title":"Planning, learning and coordination in multiagent decision processes","volume-title":"Proc. 6th Conf. Theor. Aspects Rationality Knowl.","author":"Boutilier","year":"1996"},{"key":"ref29","first-page":"1","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Velivckovic","year":"2018"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5878"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7782673\/11442848\/11247886.pdf?arnumber=11247886","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T04:48:10Z","timestamp":1773895690000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247886\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":30,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tg.2025.3629681","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"value":"2475-1502","type":"print"},{"value":"2475-1510","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}