{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T02:47:04Z","timestamp":1778122024867,"version":"3.51.4"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"A*STAR Cyber-Physical Production System (CPPS), towards Contextual and Intelligent Response Research Program RIE2020 IAF-PP","award":["A19C1a0018"],"award-info":[{"award-number":["A19C1a0018"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/tnnls.2021.3133537","type":"journal-article","created":{"date-parts":[[2021,12,22]],"date-time":"2021-12-22T20:27:02Z","timestamp":1640204822000},"page":"6146-6157","source":"Crossref","is-referenced-by-count":8,"title":["Adversary Agnostic Robust Deep Reinforcement Learning"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8072-2019","authenticated-orcid":false,"given":"Xinghua","family":"Qu","sequence":"first","affiliation":[{"name":"Bytedance AI Laboratory, Speech and Audio Team, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6080-855X","authenticated-orcid":false,"given":"Abhishek","family":"Gupta","sequence":"additional","affiliation":[{"name":"A*STAR, Singapore Institute of Manufacturing Technology (SIMTech), Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4480-169X","authenticated-orcid":false,"given":"Yew-Soon","family":"Ong","sequence":"additional","affiliation":[{"name":"Data Science and Artificial Intelligence Research Centre, Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3350-7022","authenticated-orcid":false,"given":"Zhu","family":"Sun","sequence":"additional","affiliation":[{"name":"A*STAR, Institute of High Performance Computing, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2015","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref12","first-page":"21024","article-title":"Robust deep reinforcement learning against adversarial perturbations on state observations","volume":"33","author":"zhang","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2886017"},{"key":"ref14","article-title":"Frame-correlation transfers trigger economical attacks on deep reinforcement learning policies","author":"qu","year":"2021","journal-title":"IEEE Trans Cybern"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2016.36"},{"key":"ref30","article-title":"Whatever does not kill deep reinforcement learning, makes it stronger","author":"behzadan","year":"2017","journal-title":"arXiv 1712 09344"},{"key":"ref11","article-title":"Policy distillation","author":"rusu","year":"2015","journal-title":"arXiv 1511 06295"},{"key":"ref33","article-title":"Adversarial robustness toolbox v1.0.0","author":"nicolae","year":"2018","journal-title":"arXiv 1807 01069"},{"key":"ref10","first-page":"2817","article-title":"Robust adversarial reinforcement learning","author":"pinto","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref32","article-title":"Towards deep learning models resistant to adversarial attacks","author":"madry","year":"2017","journal-title":"arXiv 1706 06083"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/robotics2030122"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref17","first-page":"2040","article-title":"Robust deep reinforcement learning with adversarial attacks","author":"pattanaik","year":"2018","journal-title":"Proc 17th Int Conf Auto Agents MultiAgent Syst (AAMAS)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206245"},{"key":"ref19","first-page":"22","article-title":"Constrained policy optimization","author":"achiam","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn (ICML)"},{"key":"ref18","first-page":"1331","article-title":"Distilling policy distillation","author":"czarnecki","year":"2019","journal-title":"Proc 22nd Int Conf Artif Intell Statist (AISTATS)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-7970-4"},{"key":"ref23","article-title":"Scaleable input gradient regularization for adversarial robustness","author":"finlay","year":"2019","journal-title":"arXiv 1905 11468"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref25","article-title":"On the effectiveness of interval bound propagation for training verifiably robust models","author":"gowal","year":"2018","journal-title":"arXiv 1810 12715"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/72.165600"},{"key":"ref22","first-page":"1","article-title":"Jacobian adversarially regularized networks for robustness","author":"chan","year":"2019","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref21","article-title":"Robust learning with Jacobian regularization","author":"hoffman","year":"2019","journal-title":"arXiv 1908 02729"},{"key":"ref28","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref27","first-page":"449","article-title":"A distributional perspective on reinforcement learning","author":"bellemare","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref29","first-page":"1","article-title":"Noisy networks for exploration","author":"fortunato","year":"2018","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref8","author":"mirman","year":"2019","journal-title":"Distilled agent DQN for provable adversarial robustness"},{"key":"ref7","article-title":"Characterizing attacks on deep reinforcement learning","author":"xiao","year":"2019","journal-title":"arXiv 1907 09470"},{"key":"ref9","article-title":"Online robustness training for deep reinforcement learning","author":"fischer","year":"2019","journal-title":"arXiv 1911 00887"},{"key":"ref4","first-page":"1","article-title":"Adversarial attacks on neural network policies","author":"huang","year":"2017","journal-title":"Proc Int Conf Learn Represent (ICLR) Workshop"},{"key":"ref3","article-title":"Toward a reinforcement learning environment toolbox for intelligent electric motor control","author":"traue","year":"2020","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.2974509"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/525"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10237282\/09660371.pdf?arnumber=9660371","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T18:29:50Z","timestamp":1695666590000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9660371\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":33,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3133537","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}