{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T20:07:30Z","timestamp":1779480450333,"version":"3.53.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Science Fund for Distinguished Young Scholars","award":["62025301"],"award-info":[{"award-number":["62025301"]}]},{"name":"National Science and Technology Major","award":["2022ZD0119702"],"award-info":[{"award-number":["2022ZD0119702"]}]},{"name":"Beijing Municipal Natural Science Foundation Undergraduate Qiyan Program","award":["QY24184"],"award-info":[{"award-number":["QY24184"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Robot."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tro.2026.3686265","type":"journal-article","created":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T19:52:04Z","timestamp":1776801124000},"page":"2146-2165","source":"Crossref","is-referenced-by-count":0,"title":["Large-Scale Multirobot Task Planning Using Efficient Hierarchical Reinforcement Learning"],"prefix":"10.1109","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0809-4234","authenticated-orcid":false,"given":"Xuan","family":"Zhou","sequence":"first","affiliation":[{"name":"State Key Lab of Autonomous Intelligent Unmanned Systems, School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2672-6128","authenticated-orcid":false,"given":"Xiang","family":"Shi","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9661-2543","authenticated-orcid":false,"given":"Lele","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Lab of Autonomous Intelligent Unmanned Systems, School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9354-6974","authenticated-orcid":false,"given":"Chen","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Lab of Autonomous Intelligent Unmanned Systems, School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4050-1755","authenticated-orcid":false,"given":"Hongbo","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Geek+ Technology Comoany, Ltd., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6446-1824","authenticated-orcid":false,"given":"Lin","family":"Ma","sequence":"additional","affiliation":[{"name":"Zhejiang Cainiao Supply Chain Management Company, Ltd., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1111-7285","authenticated-orcid":false,"given":"Fang","family":"Deng","sequence":"additional","affiliation":[{"name":"State Key Lab of Autonomous Intelligent Unmanned Systems, School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2449-9793","authenticated-orcid":false,"given":"Jie","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Lab of Autonomous Intelligent Unmanned Systems, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3583136"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3564696"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2016.2628389"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913496484"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2019.1709671"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2021.1926570"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2018.08.023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2894001"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124589"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2025.3526656"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.apm.2022.06.036"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.tre.2022.102920"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1515\/9781400874668","volume-title":"Adaptive Control Processes; a Guided Tour, Princeton Univ","author":"Bellman","year":"1961"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3453160"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2021.102154"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3335656"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2976329"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3216068"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3181948"},{"key":"ref21","first-page":"33","article-title":"Optimization and coordinated autonomy in mobile fulfillment systems","volume-title":"Proc. Workshops 25th AAAI Conf. Artif. Intell.","author":"Enright","year":"2011"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.tre.2020.102087"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3082021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3216801"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118338"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.108770"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-022-3714-4"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06419-4"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2021.105400"},{"key":"ref30","first-page":"1621","article-title":"Learning to dispatch for job shop scheduling via deep reinforcement learning","volume":"33","author":"Zhang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref31","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3221352"},{"key":"ref33","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"48","author":"Mnih","year":"2016"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi9641"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00433-9"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi9579"},{"key":"ref37","first-page":"1","article-title":"Attention, learn to solve routing problems!","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kool","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924576"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00060"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref43","first-page":"807","article-title":"All learning is local: Multi-agent learning in global reward games","author":"Chang","year":"2003","journal-title":"in Proc. 17th Int. Conf. Neural Inf. Process. Syst."},{"key":"ref44","first-page":"77290","article-title":"Counterfactual conservative Q learning for offline multi-agent reinforcement learning","volume":"36","author":"Shao","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.2017.0779"},{"key":"ref47","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4615-7286-2","volume-title":"Introduction to Algebra","volume":"8","author":"Kostrikin","year":"1982"}],"container-title":["IEEE Transactions on Robotics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8860\/11297026\/11488900.pdf?arnumber=11488900","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T19:38:24Z","timestamp":1779478704000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11488900\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/tro.2026.3686265","relation":{},"ISSN":["1552-3098","1941-0468"],"issn-type":[{"value":"1552-3098","type":"print"},{"value":"1941-0468","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}