{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T12:29:39Z","timestamp":1777984179609,"version":"3.51.4"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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":[{"name":"National Key R&D Program of China","award":["2022ZD0160201"],"award-info":[{"award-number":["2022ZD0160201"]}]},{"name":"HK RGC RIF","award":["R7030-22"],"award-info":[{"award-number":["R7030-22"]}]},{"name":"HK RGC GRF","award":["17208223"],"award-info":[{"award-number":["17208223"]}]},{"name":"HK RGC GRF","award":["17204424"],"award-info":[{"award-number":["17204424"]}]},{"name":"Huawei flagship research","award":["2023"],"award-info":[{"award-number":["2023"]}]},{"name":"SupernetAI"},{"name":"HKU-CAS Joint Laboratory for Intelligent System Software"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tmc.2025.3601531","type":"journal-article","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:31:46Z","timestamp":1755801106000},"page":"992-1008","source":"Crossref","is-referenced-by-count":1,"title":["State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4082-2060","authenticated-orcid":false,"given":"Zongyuan","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Hong Kong, Hong Kong, SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8044-2176","authenticated-orcid":false,"given":"Tianyang","family":"Duan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Hong Kong, Hong Kong, SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4463-5652","authenticated-orcid":false,"given":"Zheng","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, University of Hong Kong, Hong Kong, SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4275-3006","authenticated-orcid":false,"given":"Dong","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Hong Kong, Hong Kong, SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0844-9879","authenticated-orcid":false,"given":"Zihan","family":"Fang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0269-7940","authenticated-orcid":false,"given":"Zekai","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Hong Kong, Hong Kong, SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9900-2978","authenticated-orcid":false,"given":"Ling","family":"Xiong","sequence":"additional","affiliation":[{"name":"School of Computer and Software Engineering, Xihua University, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6258-0595","authenticated-orcid":false,"given":"Hongbin","family":"Liang","sequence":"additional","affiliation":[{"name":"National United Engineering Laboratory of Integrated and Intelligent Transportation, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7746-440X","authenticated-orcid":false,"given":"Heming","family":"Cui","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Hong Kong, Hong Kong, SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5171-739X","authenticated-orcid":false,"given":"Yong","family":"Cui","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3352613"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3279906"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3334589"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/OJVT.2024.3369691"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/s23073762"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3266643"},{"key":"ref7","first-page":"432","article-title":"SoftGym: Benchmarking deep reinforcement learning for deformable object manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Lin"},{"issue":"200","key":"ref8","first-page":"1","article-title":"Distributionally robust model-based offline reinforcement learning with near-optimal sample complexity","volume":"25","author":"Shi","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref9","article-title":"Robust deep reinforcement learning through adversarial attacks and training: A survey","author":"Schott","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00741"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3480519"},{"key":"ref12","first-page":"51719","article-title":"Content-based unrestricted adversarial attack","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref13","first-page":"26156","article-title":"Robust deep reinforcement learning through adversarial loss","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Oikarinen"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3296227"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/OJITS.2021.3118972"},{"key":"ref16","first-page":"18964","article-title":"Safety-gymnasium: A unified safe reinforcement learning benchmark","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ji"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3127960"},{"key":"ref18","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014"},{"key":"ref19","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2017"},{"key":"ref20","article-title":"Fast is better than free: Revisiting adversarial training","author":"Wong","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-023-04532-5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01585"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00957"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00284"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00444"},{"key":"ref26","article-title":"Nesterov accelerated gradient and scale invariance for adversarial attacks","author":"Lin","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3111139"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890540"},{"key":"ref29","article-title":"Adversarial attacks on neural network policies","author":"Huang","year":"2017"},{"key":"ref30","article-title":"Robust deep reinforcement learning with adversarial attacks","author":"Pattanaik","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/525"},{"key":"ref32","first-page":"1","article-title":"Toward evaluating robustness of deep reinforcement learning with continuous control","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Weng"},{"key":"ref33","first-page":"21024","article-title":"Robust deep reinforcement learning against adversarial perturbations on state observations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref35","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref36","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Achiam"},{"key":"ref37","article-title":"Adversarial attacks and defences: A survey","author":"Chakraborty","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref39","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015"},{"issue":"2","key":"ref40","doi-asserted-by":"crossref","first-page":"895","DOI":"10.1109\/LRA.2018.2792536","article-title":"Per-contact iteration method for solving contact dynamics","volume":"3","author":"Hwangbo","year":"2018","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref42","article-title":"Ensemble adversarial training: Attacks and defenses","author":"Tram\u00e8r","year":"2017"},{"key":"ref43","first-page":"7472","article-title":"Theoretically principled trade-off between robustness and accuracy","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref44","article-title":"Adv-BNN: Improved adversarial defense through robust bayesian neural network","author":"Liu","year":"2018"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/11275706\/11134099.pdf?arnumber=11134099","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T18:39:39Z","timestamp":1764873579000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11134099\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":44,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2025.3601531","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.174320032.22893766\/v1","asserted-by":"object"}]},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}