{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T23:31:56Z","timestamp":1768519916205,"version":"3.49.0"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"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":["62272357"],"award-info":[{"award-number":["62272357"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62441237"],"award-info":[{"award-number":["62441237"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24A20336"],"award-info":[{"award-number":["U24A20336"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302326"],"award-info":[{"award-number":["62302326"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Hubei","award":["2022BAA052"],"award-info":[{"award-number":["2022BAA052"]}]},{"name":"Hong Kong Research Grant Council under Collaborative Research Fund","award":["C1042-23GF"],"award-info":[{"award-number":["C1042-23GF"]}]},{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"crossref","award":["CNS-2413876"],"award-info":[{"award-number":["CNS-2413876"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Wuhan Science and Technology Joint Project for Building a Strong Transportation Country","award":["2024-2-7"],"award-info":[{"award-number":["2024-2-7"]}]},{"name":"Wuhan Science and Technology Joint Project for Building a Strong Transportation Country","award":["2023-2-7"],"award-info":[{"award-number":["2023-2-7"]}]},{"name":"Wuhan Science and Technology Project for Key Research and Development","award":["2024050702030090"],"award-info":[{"award-number":["2024050702030090"]}]},{"name":"Knowledge Innovation Program of Wuhan-Shuguang Project","award":["2023010201020323"],"award-info":[{"award-number":["2023010201020323"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Areas Commun."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/jsac.2025.3574621","type":"journal-article","created":{"date-parts":[[2025,6,2]],"date-time":"2025-06-02T14:01:31Z","timestamp":1748872891000},"page":"3426-3439","source":"Crossref","is-referenced-by-count":2,"title":["Efficient AGV Scheduling in Warehouses via Hierarchical Transformer Reinforcement Learning"],"prefix":"10.1109","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8403-1776","authenticated-orcid":false,"given":"Bingyi","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2992-2650","authenticated-orcid":false,"given":"Weizhen","family":"Han","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7253-4763","authenticated-orcid":false,"given":"Enshu","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keqin","family":"Zhong","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University at Buffalo, The State University of New York, Buffalo, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9897-1953","authenticated-orcid":false,"given":"Libing","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9318-1482","authenticated-orcid":false,"given":"Jianping","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Pokfulam, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4679-6572","authenticated-orcid":false,"given":"Chunming","family":"Qiao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University at Buffalo, The State University of New York, Buffalo, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3227102"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3530815"},{"key":"ref3","first-page":"1152","article-title":"Task and path planning for multi-agent pickup and delivery","volume-title":"Proc. Int. Joint Conf. Auton. Agents Multiagent Syst. (AAMAS)","author":"Liu"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2022.102397"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2021.105517"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2020.106749"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161310"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3221352"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17344"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.11.001"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.11.006"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/socs.v5i1.18315"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3292004"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342305"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560748"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29704"},{"key":"ref17","first-page":"1993","article-title":"Attention-based priority learning for limited time multi-agent path finding","volume-title":"Proc. 23rd Int. Conf. Auto. Agents Multiagent Syst. (AAMAS)","author":"Yang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2021.3103602"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00314"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3074883"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3301300"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/math11132802"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3233879"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3327959"},{"key":"ref25","first-page":"1","article-title":"E(3)-equivariant actor-critic methods for cooperative multi-agent reinforcement learning","volume-title":"Proc. 41st Int. Conf. Mach. Learn. (ICML)","author":"Chen"},{"key":"ref26","first-page":"1","article-title":"Efficient episodic memory utilization of cooperative multi-agent reinforcement learning","volume-title":"Proc. 12th Int. Conf. Learn. Represent. (ICLR)","author":"Na"},{"key":"ref27","first-page":"1","article-title":"Byzantine robust cooperative multi-agent reinforcement learning as a Bayesian game","volume-title":"Proc. 12th Int. Conf. Learn. Represent. (ICLR)","author":"Li"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3336156"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3313595"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3312220"},{"key":"ref31","first-page":"16509","article-title":"Multi-agent reinforcement learning is a sequence modeling problem","volume-title":"Proc. 35th Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Wen"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671998"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2024.3405002"},{"key":"ref34","first-page":"59559","article-title":"Sequential asynchronous action coordination in multi-agent systems: A Stackelberg decision transformer approach","volume-title":"Proc. 41st Int. Conf. Mach. Learn. (ICML)","author":"Zhang"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25247"},{"key":"ref36","first-page":"1","article-title":"Learning two-step hybrid policy for graph-based interpretable reinforcement learning","volume":"10","author":"Mu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref37","first-page":"13458","article-title":"Settling the variance of multi-agent policy gradients","volume-title":"Proc. 34th Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Kuba"},{"key":"ref38","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative, multi-agent games","volume-title":"Proc. 35th Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Yu"},{"key":"ref39","first-page":"1","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proc. 4th Int. Conf. Learn. Represent. (ICLR)","author":"Schulman"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3606018"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TTE.2023.3280738"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-63519-3_5"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2024.3431086"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.tre.2020.102158"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3392914"}],"container-title":["IEEE Journal on Selected Areas in Communications"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/49\/11214574\/11018506-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/49\/11214574\/11018506.pdf?arnumber=11018506","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T04:37:23Z","timestamp":1761280643000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11018506\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":45,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/jsac.2025.3574621","relation":{},"ISSN":["1558-0008","0733-8716"],"issn-type":[{"value":"1558-0008","type":"electronic"},{"value":"0733-8716","type":"print"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}