{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T14:43:30Z","timestamp":1778251410262,"version":"3.51.4"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62325405"],"award-info":[{"award-number":["62325405"]}],"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":["U19B2019"],"award-info":[{"award-number":["U19B2019"]}],"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":["M-0248"],"award-info":[{"award-number":["M-0248"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Tsinghua University Initiative Scientific Research Program"},{"name":"Tsinghua-Meituan Joint Institute for Digital Life"},{"name":"Beijing National Research Center for Information Science, Technology"},{"name":"Beijing Innovation Center for Future Chips and 2030 Innovation Megaprojects of China"},{"name":"Programme on New Generation Artificial Intelligence","award":["2021AAA0150000"],"award-info":[{"award-number":["2021AAA0150000"]}]},{"name":"internship in Tsinghua University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1109\/lra.2024.3356168","type":"journal-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:52:33Z","timestamp":1705690353000},"page":"2838-2844","source":"Crossref","is-referenced-by-count":40,"title":["<i>OmniDrones:<\/i> An Efficient and Flexible Platform for Reinforcement Learning in Drone Control"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1460-7204","authenticated-orcid":false,"given":"Botian","family":"Xu","sequence":"first","affiliation":[{"name":"Electronic Engineering Department, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7374-9491","authenticated-orcid":false,"given":"Feng","family":"Gao","sequence":"additional","affiliation":[{"name":"Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6975-0158","authenticated-orcid":false,"given":"Chao","family":"Yu","sequence":"additional","affiliation":[{"name":"Electronic Engineering Department, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6666-3906","authenticated-orcid":false,"given":"Ruize","family":"Zhang","sequence":"additional","affiliation":[{"name":"Electronic Engineering Department, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9057-5817","authenticated-orcid":false,"given":"Yi","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6108-5157","authenticated-orcid":false,"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"Electronic Engineering Department, Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.9785\/cri-2015-0302"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2720851"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3057046"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636053"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160836"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref7","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019"},{"key":"ref8","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","year":"2022"},{"key":"ref9","first-page":"91","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","volume-title":"Proc. 5th Conf. Robot Learn.","author":"Rudin","year":"2022"},{"key":"ref10","first-page":"5150","article-title":"Towards human-level bimanual dexterous manipulation with reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2792536"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref13","article-title":"Isaac gym: High performance GPU-based physics simulation for robot learning","volume-title":"Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks","volume":"1","author":"Makoviychuk","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3270034"},{"key":"ref15","first-page":"1147","article-title":"Flightmare: A flexible quadrotor simulator","volume-title":"Proc. Conf. Robot Learn.","author":"Song","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67361-5_40"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389727"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1007\/978-3-319-26054-9_23","article-title":"RotorsA modular Gazebo MAV simulator framework","volume-title":"Robot Operating System (ROS)","author":"Furrer","year":"2016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20190-6_4"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/iros51168.2021.9635857"},{"key":"ref21","article-title":"Pybullet, a Python module for physics simulation for games, robotics and machine learning","author":"Coumans","year":"2016"},{"key":"ref22","article-title":"Aerial GymIsaac Gym simulator for aerial robots","author":"Kulkarni","year":"2023"},{"key":"ref23","article-title":"Torchrl: A data-driven decision-making library for pytorch","author":"Bou","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487175"},{"issue":"1","key":"ref25","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3301273"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2930489"},{"key":"ref28","first-page":"133","article-title":"Deep drone racing: Learning agile flight in dynamic environments","volume-title":"Proc. Conf. Robot Learn.","author":"Kaufmann","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811564"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968116"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MED.2018.8442759"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2010.5717652"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981140"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2793344"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref36","article-title":"Deepmind control suite","volume-title":"Softw. Impacts","volume":"6","author":"Tunyasuvunakool","year":"2018"},{"key":"ref37","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref38","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2018"},{"key":"ref39","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2018"},{"key":"ref40","first-page":"1","article-title":"Trust region policy optimisation in multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kuba","year":"2022"},{"key":"ref41","first-page":"1","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lowe","year":"2017"},{"issue":"1","key":"ref42","first-page":"7234","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref43","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.011"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10409903\/10409589.pdf?arnumber=10409589","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T18:42:02Z","timestamp":1725561722000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10409589\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":44,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3356168","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3]]}}}