{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T17:19:06Z","timestamp":1784913546441,"version":"3.55.0"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2023YFB4301904"],"award-info":[{"award-number":["2023YFB4301904"]}]},{"name":"National Key R&D Program of China","award":["2022YFE0208000"],"award-info":[{"award-number":["2022YFE0208000"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52372319"],"award-info":[{"award-number":["52372319"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Key Lab of Vehicle Aerodynamics and Vehicle Thermal Management Systems"},{"name":"National Key R&D Program of China","award":["2023YFB4301904"],"award-info":[{"award-number":["2023YFB4301904"]}]},{"name":"National Key R&D Program of China","award":["2022YFE0208000"],"award-info":[{"award-number":["2022YFE0208000"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52372319"],"award-info":[{"award-number":["52372319"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Key Lab of Vehicle Aerodynamics and Vehicle Thermal Management Systems"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tmc.2025.3526979","type":"journal-article","created":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T20:42:01Z","timestamp":1736368921000},"page":"5016-5030","source":"Crossref","is-referenced-by-count":10,"title":["Cooperative Path Planning With Asynchronous Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6896-8284","authenticated-orcid":false,"given":"Jiaming","family":"Yin","sequence":"first","affiliation":[{"name":"Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6644-0349","authenticated-orcid":false,"given":"Weixiong","family":"Rao","sequence":"additional","affiliation":[{"name":"Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4517-3779","authenticated-orcid":false,"given":"Yu","family":"Xiao","sequence":"additional","affiliation":[{"name":"Aalto University, Espoo, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0476-0512","authenticated-orcid":false,"given":"Keshuang","family":"Tang","sequence":"additional","affiliation":[{"name":"Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/VNC.2016.7835942"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3557915.3561005"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-45528-0"},{"key":"ref4","first-page":"671","article-title":"Packet routing in dynamically changing networks: A reinforcement learning approach","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Boyan"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MDM.2019.00-45"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/BF01386390"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-218X(97)00121-2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1142\/S0129183198000303"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCWorkshops50388.2021.9473555"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSSC.1968.300136"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS51616.2021.00056"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.32473\/flairs.v35i.130584"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1080\/15568318.2022.2076633"},{"key":"ref16","article-title":"Inrix 2023 global traffic scorecard","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.trd.2017.06.015"},{"key":"ref18","article-title":"METIS: Unstructured graph partitioning and sparse matrix ordering system","author":"Karypis","year":"1997"},{"key":"ref19","first-page":"7166","article-title":"Attention, learn to solve routing problems!","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Kool"},{"key":"ref20","first-page":"798","article-title":"ASM-PPO: Asynchronous and scalable multi-agent PPO for cooperative charging","volume-title":"Proc. 21st Int. Conf. Auton. Agents Multiagent Syst.","author":"Liang"},{"key":"ref21","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. 4th Int. Conf. Learn. Representations","author":"Lillicrap"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569938"},{"key":"ref23","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 30: Annu. Conf. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04105-y"},{"key":"ref26","article-title":"Dealing with non-stationarity in multi-agent deep reinforcement learning","author":"Papoudakis","year":"2019"},{"key":"ref27","first-page":"4292","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Rashid"},{"key":"ref28","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1117\/12.2585808"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103560"},{"key":"ref31","first-page":"5887","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. Mach. Learn. Res.","author":"Son"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599839"},{"key":"ref33","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2013.27"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3152434.3152441"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref38","first-page":"2920","article-title":"Graph attention networks","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Velickovic"},{"key":"ref39","first-page":"2692","article-title":"Pointer networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vinyals"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/60"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ISC255366.2022.9922404"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/MDM52706.2021.00040"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3258974"},{"key":"ref44","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref45","first-page":"1107","article-title":"Asynchronous multi-agent reinforcement learning for efficient real-time multi-robot cooperative exploration","volume-title":"Proc. 2023 Int. Conf. Auton. Agents Multiagent Syst.","author":"Yu"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS47876.2019.00072"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/10990048\/10833653.pdf?arnumber=10833653","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T04:23:42Z","timestamp":1746678222000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10833653\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":46,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2025.3526979","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}