{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T18:33:34Z","timestamp":1770230014553,"version":"3.49.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611002","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"5169-5175","source":"Crossref","is-referenced-by-count":5,"title":["REFORMA: Robust REinFORceMent Learning via Adaptive Adversary for Drones Flying under Disturbances"],"prefix":"10.1109","author":[{"given":"Hao-Lun","family":"Hsu","sequence":"first","affiliation":[{"name":"Duke University,Department of Computer Science,Durham,NC,USA,27708"}]},{"given":"Haocheng","family":"Meng","sequence":"additional","affiliation":[{"name":"Duke University,Department of Electrical and Computer Engineering,Durham,NC,USA,27708"}]},{"given":"Shaocheng","family":"Luo","sequence":"additional","affiliation":[{"name":"Duke University,Department of Electrical and Computer Engineering,Durham,NC,USA,27708"}]},{"given":"Juncheng","family":"Dong","sequence":"additional","affiliation":[{"name":"Duke University,Department of Electrical and Computer Engineering,Durham,NC,USA,27708"}]},{"given":"Vahid","family":"Tarokh","sequence":"additional","affiliation":[{"name":"Duke University,Department of Electrical and Computer Engineering,Durham,NC,USA,27708"}]},{"given":"Miroslav","family":"Pajic","sequence":"additional","affiliation":[{"name":"Duke University,Department of Computer Science,Durham,NC,USA,27708"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WOCN.2016.7759885"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS.2019.8798337"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/DCOSS.2019.00113"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635857"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2021.11.158"},{"key":"ref6","article-title":"Robust reinforcement learning algorithm for vision-based ship landing of uavs","author":"Vishnu","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981152"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3296227"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SCCC57464.2022.10000286"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3118949"},{"key":"ref11","first-page":"2817","article-title":"Robust adversarial reinforcement learning","volume-title":"International conference on machine learning","author":"Pinto"},{"issue":"6","key":"ref12","first-page":"4015","article-title":"Robust reinforcement learning via adversarial training with langevin dynamics","volume":"9","author":"Kamalaruban","year":"2021","journal-title":"IEEE Internet of Things Journal"},{"key":"ref13","first-page":"6215","article-title":"Action robust reinforcement learning and applications in continuous control","volume-title":"International Conference on Machine Learning","author":"Tessler"},{"key":"ref14","article-title":"Robust reinforcement learning through efficient adversarial herding","author":"Dong","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2021.XVII.061","article-title":"Blind bipedal stair traversal via sim-to-real reinforcement learning","author":"Siekmann","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.011"},{"key":"ref18","first-page":"1722","article-title":"In-hand object rotation via rapid motor adaptation","volume-title":"Conference on Robot Learning","author":"Qi"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160836"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.brs.2021.10.232"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPS54341.2022.00014"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3576841.3585925"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3194808"},{"key":"ref24","article-title":"Sparc: adaptive closed-loop control of vagal nerve stimulation for regulating cardiovascular function using deep reinforcement learning: a computational study","volume-title":"2021 Neuroscience Meeting (SFN)","author":"Sarikhani"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342062"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3286171"},{"key":"ref27","article-title":"D2t2: Decision transformer with temporal difference via steering guidance","author":"Hsu","year":"2024"},{"key":"ref28","article-title":"Fine-tuning language models from human preferences","author":"Ziegler","year":"2019"},{"key":"ref29","article-title":"Towards interpretable deep reinforcement learning with human-friendly prototypes","volume-title":"International Conference on Learning Representations","author":"Kenny"},{"key":"ref30","article-title":"Accelerating safe reinforcement learning with constraint-mismatched policies","volume-title":"International Conference on Machine Learning (ICML)","author":"Yang"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812181"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/make4010013"},{"key":"ref33","article-title":"Solving uncertain markov decision processes","volume-title":"Citeseer","author":"Bagnell"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1040.0129"},{"key":"ref35","first-page":"1162","article-title":"Active domain randomization","volume-title":"Conference on Robot Learning","author":"Mehta"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2021.01.003"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/machines11030352"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3390\/drones6090220"},{"key":"ref39","first-page":"1655","article-title":"Robust nonlinear output feedback control of a 6-dof quadrotor uav","volume-title":"2019 12th Asian Control Conference (ASCC)","author":"Steinbusch"},{"key":"ref40","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.adhoc.2018.11.004"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611002.pdf?arnumber=10611002","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:23:06Z","timestamp":1723267386000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611002\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611002","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}