{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T01:54:00Z","timestamp":1779933240215,"version":"3.53.1"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,3,15]],"date-time":"2025-03-15T00:00:00Z","timestamp":1741996800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,15]],"date-time":"2025-03-15T00:00:00Z","timestamp":1741996800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,15]],"date-time":"2025-03-15T00:00:00Z","timestamp":1741996800000},"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":["52102438"],"award-info":[{"award-number":["52102438"]}],"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":["52072243"],"award-info":[{"award-number":["52072243"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2022M711803"],"award-info":[{"award-number":["2022M711803"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2024T170482"],"award-info":[{"award-number":["2024T170482"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2025,3,15]]},"DOI":"10.1109\/jiot.2024.3497185","type":"journal-article","created":{"date-parts":[[2024,11,13]],"date-time":"2024-11-13T18:58:08Z","timestamp":1731524288000},"page":"7577-7589","source":"Crossref","is-referenced-by-count":2,"title":["Data-Efficient Learning-Based Iterative Optimization Method With Time-Varying Prediction Horizon for Multiagent Collaboration"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8468-7908","authenticated-orcid":false,"given":"Bowen","family":"Wang","sequence":"first","affiliation":[{"name":"School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3316-0354","authenticated-orcid":false,"given":"Xinle","family":"Gong","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4880-5054","authenticated-orcid":false,"given":"Yafei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4619-9679","authenticated-orcid":false,"given":"Rongtao","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongcheng","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/00207721.2023.2250041"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2024.101364"},{"key":"ref3","article-title":"Multi-agent reinforcement learning for autonomous driving: A survey","author":"Zhang","year":"2024","journal-title":"arXiv:2408.09675"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.11591\/ijece.v12i4.pp3517-3529"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3284756"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1515\/auto-2020-0004"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611037"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3306572"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abm5954"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04105-y"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2019.2908899"},{"key":"ref12","first-page":"32253","article-title":"LipsNet: A smooth and robust neural network with adaptive Lipschitz constant for high accuracy optimal control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Song"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2024.3364428"},{"key":"ref14","first-page":"30776","article-title":"Complementary attention for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shao"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref16","first-page":"486","article-title":"A theoretical analysis of deep Q-learning","volume-title":"Proc. Learn. Dyn. Control","author":"Fan"},{"key":"ref17","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1002\/int.22466"},{"key":"ref19","article-title":"An introduction to centralized training for decentralized execution in cooperative multi-agent reinforcement learning","author":"Amato","year":"2024","journal-title":"arXiv:2409.03052"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI56018.2022.00183"},{"key":"ref21","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.","volume":"33","author":"Rashid"},{"key":"ref22","first-page":"11920","article-title":"Reinforcement learning with prototypical representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yarats"},{"key":"ref23","first-page":"104","article-title":"An optimistic perspective on offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Agarwal"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(89)90002-2"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3237547"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1017\/9781139061759"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812369"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-090419-075625"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2021.10.006"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2023.3237999"},{"key":"ref32","article-title":"Mixed reinforcement learning with additive stochastic uncertainty","author":"Mu","year":"2020","journal-title":"arXiv:2003.00848"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.23919\/ICCAS50221.2020.9268413"},{"key":"ref34","first-page":"1","article-title":"Hybrid reward architecture for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Van Seijen"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3314762"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2022.05.017"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IV51971.2022.9827073"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3063927"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-7784-8"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2023.3275732"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2753460"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2017.7963748"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9303820"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9303903"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3083559"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2023.111014"},{"key":"ref47","first-page":"2206","article-title":"Improving language models by retrieving from trillions of tokens","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Borgeaud"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref49","article-title":"Is long horizon reinforcement learning more difficult than short horizon reinforcement learning?","author":"Wang","year":"2020","journal-title":"arXiv:2005.00527"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2018.07.250"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/10918322\/10752569.pdf?arnumber=10752569","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T17:50:58Z","timestamp":1741629058000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10752569\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,15]]},"references-count":50,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2024.3497185","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,15]]}}}