{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:16:01Z","timestamp":1776885361924,"version":"3.51.2"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["22511105500"],"award-info":[{"award-number":["22511105500"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172299"],"award-info":[{"award-number":["62172299"]}],"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":["62032019"],"award-info":[{"award-number":["62032019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2023-4-YB-05"],"award-info":[{"award-number":["2023-4-YB-05"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Veh."],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1109\/tiv.2023.3307134","type":"journal-article","created":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T17:48:31Z","timestamp":1692726511000},"page":"1615-1627","source":"Crossref","is-referenced-by-count":34,"title":["Robust Multi-Agent Reinforcement Learning Method Based on Adversarial Domain Randomization for Real-World Dual-UAV Cooperation"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8094-889X","authenticated-orcid":false,"given":"Shutong","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Computer Science, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7523-4827","authenticated-orcid":false,"given":"Guanjun","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2649-8666","authenticated-orcid":false,"given":"Ziyuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4573-8968","authenticated-orcid":false,"given":"Kaiwen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6601-3515","authenticated-orcid":false,"given":"Jiacun","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Software Engineering, Monmouth University, West Long Branch, NJ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2023.3270165"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2023.3274671"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2023.3279296"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3237570"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2982168"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2890773"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2933002"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3023733"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3088718"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2023.3271667"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3112718"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3163971"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1142\/S2301385020500090"},{"key":"ref16","article-title":"Multi-agent reinforcement learning: Methods, applications, visionary prospects, and challenges","author":"Zhou","year":"2023"},{"key":"ref17","article-title":"Online deep reinforcement learning for autonomous UAV navigation and exploration of outdoor environments","author":"Maciel-Pearson","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974648"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2020.3027695"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3278715"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.2514\/1.G004106"},{"key":"ref22","article-title":"Cooperative and distributed reinforcement learning of drones for field coverage","author":"Pham","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/AERO47225.2020.9172262"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/drones7070476"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230632"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-2635-8_71"},{"issue":"19","key":"ref27","article-title":"Multiagent reinforcement learning based on fusion-multiactor-attention-critic for multiple-unmanned-aerial-vehicle navigation control","volume-title":"Energies","volume":"15","author":"Jeon","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3180288"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981319"},{"key":"ref31","first-page":"1162","article-title":"Active domain randomization","volume-title":"Proc. Conf. Robot Learn.","author":"Mehta","year":"2020"},{"key":"ref32","article-title":"Generating automatic curricula via self-supervised active domain randomization","author":"Raparthy","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3052391"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref35","article-title":"Prioritized experience replay","author":"Schaul","year":"2016"},{"key":"ref36","article-title":"Prioritized sequence experience replay","author":"Brittain","year":"2019"},{"key":"ref37","first-page":"110","article-title":"Experience replay with likelihood-free importance weights","volume-title":"Proc. 4th Annu. Conf. Learn. Dyn. Control","author":"Sinha","year":"2022"},{"key":"ref38","first-page":"157","article-title":"Markov games as a framework for multi-agent reinforcement learning","volume-title":"Proc. Mach. Learn.","author":"Cohen","year":"1994"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.32917\/hmj\/1206139508"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3229213"},{"key":"ref41","article-title":"R-MADDPG for partially observable environments and limited communication","author":"Wang","year":"2020"},{"key":"ref42","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Lowe","year":"2017"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3022638"},{"key":"ref44","article-title":"Guided domain randomization with meta reinforcement learning","author":"Ibrahim","year":"2022"},{"key":"ref45","first-page":"10571","article-title":"Robust multi-agent reinforcement learning with model uncertainty","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Zhang","year":"2020"},{"key":"ref46","article-title":"Openai gym","author":"Brockman","year":"2016"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1177\/17568293231158443"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1002\/dac.5334"}],"container-title":["IEEE Transactions on Intelligent Vehicles"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274857\/10443740\/10225713.pdf?arnumber=10225713","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T17:45:23Z","timestamp":1750959923000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10225713\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":48,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tiv.2023.3307134","relation":{},"ISSN":["2379-8904","2379-8858"],"issn-type":[{"value":"2379-8904","type":"electronic"},{"value":"2379-8858","type":"print"}],"subject":[],"published":{"date-parts":[[2024,1]]}}}