{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T19:16:32Z","timestamp":1772910992136,"version":"3.50.1"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["BX20220071"],"award-info":[{"award-number":["BX20220071"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2022M720769"],"award-info":[{"award-number":["2022M720769"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China","award":["2021ZD0113502"],"award-info":[{"award-number":["2021ZD0113502"]}]},{"name":"National Key R&D Program of China","award":["2021ZD0113503"],"award-info":[{"award-number":["2021ZD0113503"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/lra.2024.3472348","type":"journal-article","created":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T17:25:18Z","timestamp":1727976318000},"page":"10248-10255","source":"Crossref","is-referenced-by-count":1,"title":["Robust Proximal Adversarial Reinforcement Learning Under Model Mismatch"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1374-7969","authenticated-orcid":false,"given":"Peng","family":"Zhai","sequence":"first","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}]},{"given":"Xiaoyi","family":"Wei","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2741-0494","authenticated-orcid":false,"given":"Taixian","family":"Hou","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3920-8362","authenticated-orcid":false,"given":"Xiaopeng","family":"Ji","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9459-1889","authenticated-orcid":false,"given":"Zhiyan","family":"Dong","sequence":"additional","affiliation":[{"name":"Ji Hua Laboratory, Foshan, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4560-4267","authenticated-orcid":false,"given":"Jiafu","family":"Yi","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Hainan University, Hainan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0467-4347","authenticated-orcid":false,"given":"Lihua","family":"Zhang","sequence":"additional","affiliation":[{"name":"Engineering Research Center of AI and Robotics, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cirpj.2022.11.003"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09997-9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3112718"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3126658"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IRC.2019.00120"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/robotics9010008"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3220531"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/0899766053011528"},{"key":"ref11","first-page":"2817","article-title":"Robust adversarial reinforcement learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Pinto","year":"2017"},{"key":"ref12","first-page":"6215","article-title":"Action robust reinforcement learning and applications in continuous control","volume-title":"Proc. Mach. Learn. Res.","volume":"97","author":"Tessler","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/430"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2023.3289334"},{"key":"ref15","first-page":"1","article-title":"Adversarial attacks on neural network policies","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Huang","year":"2017"},{"key":"ref16","first-page":"1","article-title":"Delving into adversarial attacks on deep policies","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kos","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5887"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.2974509"},{"key":"ref19","first-page":"2040","article-title":"Robust deep reinforcement learning with adversarial attacks","volume-title":"Proc. 17th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Pattanaik","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147846"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892901"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1186\/s42400-019-0027-x"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/make4010013"},{"key":"ref24","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref25","first-page":"91","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","volume-title":"Proc. 5th Conf. Robot Learn.","volume":"164","author":"Rudin","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2976639"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3301273"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196611"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-32552-1_26"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10683798\/10702590.pdf?arnumber=10702590","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T14:11:23Z","timestamp":1728569483000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10702590\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":29,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3472348","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}