{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T19:12:18Z","timestamp":1764270738212,"version":"3.46.0"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022YFE0112300"],"award-info":[{"award-number":["2022YFE0112300"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62373375","U2341216"],"award-info":[{"award-number":["62373375","U2341216"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/tai.2024.3443783","type":"journal-article","created":{"date-parts":[[2024,8,14]],"date-time":"2024-08-14T13:46:46Z","timestamp":1723643206000},"page":"25-36","source":"Crossref","is-referenced-by-count":1,"title":["Reinforcement Learned Multiagent Cooperative Navigation in Hybrid Environment With Relational Graph Learning"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9092-5276","authenticated-orcid":false,"given":"Wen","family":"Ou","sequence":"first","affiliation":[{"name":"School of Automation, Central South University, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3353-2586","authenticated-orcid":false,"given":"Biao","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Automation, Central South University, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4795-9967","authenticated-orcid":false,"given":"Xiaodong","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Automation, Central South University, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0676-7344","authenticated-orcid":false,"given":"Yu","family":"Feng","sequence":"additional","affiliation":[{"name":"Information engineering College, Zhejiang University of Technology, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0261-9782","authenticated-orcid":false,"given":"Yuqian","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Automation, Central South University, Changsha, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15406\/iratj.2017.02.00023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MED.2017.7984200"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3124093"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.11.006"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225009"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/027836499801700706"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543489"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19457-3_1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5652073"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2011.2120810"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32723-0_15"},{"key":"ref12","first-page":"147","article-title":"Multi-robot collision avoidance with localization uncertainty","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst.","volume":"1","author":"Hennes","year":"2012"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-018-9726-5"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5654369"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794134"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561595"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202312"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593871"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3161699"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340876"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812341"},{"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","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/app9153057"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/machines9040077"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2903261"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062803"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636349"},{"key":"ref29","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2016"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3260710"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3220798"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197209"},{"key":"ref33","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","year":"2018"},{"key":"ref34","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":"ref35","first-page":"10199","article-title":"Weighted QMIX: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rashid","year":"2020"},{"key":"ref36","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"},{"article-title":"QPLEX: Duplex dueling multi-agent q-learning","year":"2020","author":"Wang","key":"ref37"},{"author":"Yang","key":"ref38","article-title":"Qatten: A general framework for cooperative multiagent reinforcement learning"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"author":"Schulman","key":"ref42","article-title":"Proximal policy optimization algorithms"},{"key":"ref43","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":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3076021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2023.3268612"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3195818"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340705"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2972868"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03191-2"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.06.006"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3213604"},{"author":"Veli\u010dkovi\u0107","key":"ref52","article-title":"Graph attention networks"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3221912"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.573"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"author":"Chung","key":"ref56","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling"},{"author":"Brockman","key":"ref57","article-title":"OpenAI gym"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9078688\/10841832\/10636265.pdf?arnumber=10636265","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T19:01:00Z","timestamp":1764270060000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10636265\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":57,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tai.2024.3443783","relation":{},"ISSN":["2691-4581"],"issn-type":[{"type":"electronic","value":"2691-4581"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}