{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T05:00:02Z","timestamp":1780462802193,"version":"3.54.1"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Guang Dong Basic and Applied Basic Research Foundation","award":["2023A1515011813"],"award-info":[{"award-number":["2023A1515011813"]}]},{"name":"Guang Dong Basic and Applied Basic Research Foundation","award":["2020B515130004"],"award-info":[{"award-number":["2020B515130004"]}]},{"name":"National Natural Science Funds of China for Young Scholar","award":["62003328"],"award-info":[{"award-number":["62003328"]}]},{"name":"National Natural Science Funds of China for Young Scholar","award":["62073311"],"award-info":[{"award-number":["62073311"]}]},{"name":"Shenzhen Basic Key Research Project","award":["JCYJ20200109115414354"],"award-info":[{"award-number":["JCYJ20200109115414354"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/lra.2024.3410159","type":"journal-article","created":{"date-parts":[[2024,6,5]],"date-time":"2024-06-05T18:01:43Z","timestamp":1717610503000},"page":"6624-6631","source":"Crossref","is-referenced-by-count":14,"title":["Limited Information Aggregation for Collaborative Driving in Multi-Agent Autonomous Vehicles"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3823-6828","authenticated-orcid":false,"given":"Qingyi","family":"Liang","sequence":"first","affiliation":[{"name":"Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2363-8798","authenticated-orcid":false,"given":"Jia","family":"Liu","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6498-0234","authenticated-orcid":false,"given":"Zhengmin","family":"Jiang","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianwen","family":"Yin","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1112-209X","authenticated-orcid":false,"given":"Kun","family":"Xu","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0157-1393","authenticated-orcid":false,"given":"Huiyun","family":"Li","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lowe","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00175"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2022.3174410"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2024.3352543"},{"key":"ref6","first-page":"7613","article-title":"MAVEN: Multi-agent variational exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Mahajan","year":"2019"},{"key":"ref7","article-title":"Communication in multi-agent reinforcement learning: Intention sharing","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kim","year":"2020"},{"key":"ref8","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. 17th Int. Conf. Auton. Agents and MultiAgent Syst.","author":"Sunehag","year":"2018"},{"key":"ref9","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","year":"2019"},{"issue":"1","key":"ref10","first-page":"7234","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":"ref11","first-page":"2145","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Foerster","year":"2016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref13","first-page":"1046","article-title":"Trust region policy optimisation in multi-agent reinforcement learning","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Kuba","year":"2022"},{"key":"ref14","first-page":"398","article-title":"Emergent behaviors in mixed-autonomy traffic","volume-title":"Proc. Conf. Robot Learn.","author":"Wu","year":"2017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461233"},{"key":"ref16","article-title":"CM3: Cooperative multi-goal multi-stage multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang","year":"2020"},{"key":"ref17","first-page":"10784","article-title":"Learning to simulate self-driven particles system with coordinated policy optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Peng","year":"2021"},{"key":"ref18","first-page":"13121","article-title":"Biases for emergent communication in multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Eccles","year":"2019"},{"key":"ref19","first-page":"15230","article-title":"Learning to ground multi-agent communication with autoencoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Lin","year":"2021"},{"key":"ref20","first-page":"2252","article-title":"Learning multiagent communication with backpropagation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Sukhbaatar","year":"2016"},{"key":"ref21","first-page":"946","article-title":"Socially-attentive policy optimization in multi-agent self-driving system","volume-title":"Proc. Conf. Robot Learn.","author":"Dai","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2936167"},{"key":"ref23","first-page":"25476","article-title":"Mastering atari games with limited data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ye","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1002\/per.2410020304"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/RCAR58764.2023.10249648"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3190471"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref29","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lillicrap","year":"2015"},{"key":"ref30","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","year":"2022"},{"key":"ref31","article-title":"Is independent learning all you need in the starcraft multi-agent challenge","author":"de Witt","year":"2020"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10534628\/10549763.pdf?arnumber=10549763","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T19:01:19Z","timestamp":1750100479000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10549763\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":31,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3410159","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}