{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T18:49:22Z","timestamp":1784746162902,"version":"3.55.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Key Fields Research and Development Project of Guangdong Province","award":["2020B0101380001"],"award-info":[{"award-number":["2020B0101380001"]}]},{"name":"Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies","award":["2022B1212010005"],"award-info":[{"award-number":["2022B1212010005"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61902093"],"award-info":[{"award-number":["61902093"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong","doi-asserted-by":"publisher","award":["2020A1515010652"],"award-info":[{"award-number":["2020A1515010652"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Foundational Research Funding","award":["20200805173048001"],"award-info":[{"award-number":["20200805173048001"]}]},{"name":"CCF-Tencent Open Fund","award":["RAGR20210105"],"award-info":[{"award-number":["RAGR20210105"]}]},{"name":"PINGAN-HITsz Intelligence Finance Research Center"},{"name":"Ricoh-HITsz Joint Research Center"},{"name":"GBase-HITsz Joint Research Center"},{"name":"Pengcheng Cloud Brain"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1109\/tnnls.2022.3197918","type":"journal-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T20:02:54Z","timestamp":1665432174000},"page":"3769-3779","source":"Crossref","is-referenced-by-count":15,"title":["Cascaded Attention: Adaptive and Gated Graph Attention Network for Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6903-145X","authenticated-orcid":false,"given":"Shuhan","family":"Qi","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology Shenzhen, Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2466-4990","authenticated-orcid":false,"given":"Xinhao","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7427-8764","authenticated-orcid":false,"given":"Peixi","family":"Peng","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuzhong","family":"Huang","sequence":"additional","affiliation":[{"name":"DiDi, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6611-2046","authenticated-orcid":false,"given":"Jiajia","family":"Zhang","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3512-0649","authenticated-orcid":false,"given":"Xuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref2","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2975035"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2997523"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2945019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5744"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2996209"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3025711"},{"key":"ref10","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. NeurIPS","author":"Foerster"},{"key":"ref11","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","volume-title":"Proc. NeurIPS","author":"Sukhbaatar"},{"key":"ref12","first-page":"7265","article-title":"Learning attentional communication for multi-agent cooperation","volume-title":"Proc. NeurIPS","author":"Jiang"},{"key":"ref13","first-page":"1538","article-title":"TarMAC: Targeted multi-agent communication","volume-title":"Proc. ICML","author":"Das"},{"key":"ref14","first-page":"330","article-title":"Multi-agent reinforcement learning: Independent versus cooperative agents","volume-title":"Proc. ICML","author":"Tan"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888912000057"},{"key":"ref17","first-page":"5567","article-title":"Mean field multi-agent reinforcement learning","volume-title":"Proc. ICML","author":"Yang"},{"key":"ref18","first-page":"2701","article-title":"VAIN: Attentional multi-agent predictive modeling","volume-title":"Proc. NeurIPS","author":"Hoshen"},{"key":"ref19","first-page":"4502","article-title":"Interaction networks for learning about objects, relations and physics","volume-title":"Proc. NeurIPS","author":"Battaglia"},{"key":"ref20","first-page":"1","article-title":"Neural machine translation by jointly learning to align and translate","volume-title":"Proc. ICLR","author":"Bahdanau"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref22","first-page":"1","article-title":"Learning when to communicate at scale in multiagent cooperative and competitive tasks","volume-title":"Proc. ICLR","author":"Singh"},{"key":"ref23","first-page":"456","article-title":"Learning correlated communication topology in multi-agent reinforcement learning","volume-title":"Proc. AAMAS","author":"Du"},{"key":"ref24","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. NeurIPS","author":"Lowe"},{"key":"ref25","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. ICLR","author":"Lillicrap"},{"key":"ref26","first-page":"1","article-title":"Multiagent soft Q-learning","volume-title":"Proc. AAAI Spring Symposia","author":"Wei"},{"key":"ref27","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"Proc. ICML","author":"Iqbal"},{"key":"ref28","first-page":"1856","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. ICML","author":"Haarnoja"},{"key":"ref29","first-page":"339","article-title":"GaAN: Gated attention networks for learning on large and spatiotemporal graphs","volume-title":"Proc. UAI","author":"Zhang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-36808-1_35"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107535"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2920905"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2647904"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2829867"},{"key":"ref35","first-page":"1","article-title":"Graph convolutional reinforcement learning","volume-title":"Proc. ICLR","author":"Jiang"},{"key":"ref36","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. ICML","author":"Mnih"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6214"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6211"},{"key":"ref39","first-page":"964","article-title":"Multi-agent graph-attention communication and teaming","volume-title":"Proc. AAMAS","author":"Niu"},{"key":"ref40","first-page":"1741","article-title":"Learning transferable cooperative behavior in multi-agent teams","volume-title":"Proc. AAMAS","author":"Agarwal"},{"key":"ref41","first-page":"1","article-title":"Graph attention networks","volume-title":"Proc. ICLR","author":"Velickovic"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref43","article-title":"Proximal policy optimization algorithms","volume-title":"arXiv:1707.06347","author":"Schulman","year":"2017"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2005.1555942"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref46","article-title":"Relational inductive biases, deep learning, and graph networks","volume-title":"arXiv:1806.01261","author":"Battaglia","year":"2018"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref49","article-title":"Multiagent bidirectionally-coordinated nets: Emergence of human-level coordination in learning to play StarCraft combat games","volume-title":"arXiv:1703.10069","author":"Peng","year":"2017"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10454107\/09913678.pdf?arnumber=9913678","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T04:00:34Z","timestamp":1725249634000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9913678\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":50,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3197918","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3]]}}}