{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T07:18:53Z","timestamp":1780989533191,"version":"3.54.1"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62173251"],"award-info":[{"award-number":["62173251"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Provincial Key Laboratory of Intelligent Decision and Cooperative Control"},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","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":[[2024,6]]},"DOI":"10.1109\/tnnls.2022.3220798","type":"journal-article","created":{"date-parts":[[2022,11,16]],"date-time":"2022-11-16T20:38:50Z","timestamp":1668631130000},"page":"7767-7777","source":"Crossref","is-referenced-by-count":29,"title":["A Local-and-Global Attention Reinforcement Learning Algorithm for Multiagent Cooperative Navigation"],"prefix":"10.1109","volume":"35","author":[{"given":"Chunwei","family":"Song","sequence":"first","affiliation":[{"name":"College of Electronics and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zichen","family":"He","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6737-1381","authenticated-orcid":false,"given":"Lu","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3024655"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3050960"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2996209"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3124466"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917741532"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/app9153057"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/machines9040077"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461113"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920916531"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2903261"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062803"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202312"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3050338"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3089493"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref17","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":"ref18","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. 17th Int. Conf. Auto. Agents MultiAgent Syst.","author":"Sunehag"},{"key":"ref19","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":"ref20","doi-asserted-by":"publisher","DOI":"10.1177\/0142331216645176"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2021.02.006"},{"key":"ref22","first-page":"1","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref23","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lowe"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2103.01955"},{"key":"ref26","article-title":"Emergence of locomotion behaviours in rich environments","author":"Heess","year":"2017","journal-title":"arXiv:1707.02286"},{"key":"ref27","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2005.12729"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref30","article-title":"Synthesizer: Rethinking self-attention in transformer models","author":"Tay","year":"2020","journal-title":"arXiv:2005.00743"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref32","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3172168"},{"key":"ref34","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref35","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Iqbal"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10547160\/09953939.pdf?arnumber=9953939","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,5]],"date-time":"2024-06-05T18:02:53Z","timestamp":1717610573000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9953939\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":35,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3220798","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}