Protecting Reward Function of Reinforcement Learning via Minimal and Non-catastrophic Adversarial Trajectory Chen, T, Xiang, Y, Li, Y, Tian, Y, Tong, E, Niu, W, Liu, J, Li, Gang and Alfred Chen, Q 2021, Protecting Reward Function of Reinforcement Learning via Minimal and Non-catastrophic Adversarial Trajectory, in SRDS 2021: Proceedings of the 40th Reliable Distributed Systems 2021 International Symposium, IEEE, Piscataway, N.J., pp. 299-309, doi: 10.1109/SRDS53918.2021.00037. Attached Files Name Description MIMEType Size Downloads Title Protecting Reward Function of Reinforcement Learning via Minimal and Non-catastrophic Adversarial Trajectory Author(s) Chen, T Xiang, Y Li, Y Tian, Y Tong, E Niu, W Liu, J Li, Gang orcid.org/0000-0003-1583-641X Alfred Chen, Q Conference name IEEE Reliable Distributed Systems : Symposium (2021 : Chicago, Ill.) Conference location Chicago, Ill. Conference dates 2021/09/20 - 2021/09/23 Title of proceedings SRDS 2021: Proceedings of the 40th Reliable Distributed Systems 2021 International Symposium Publication date 2021-01-01 Series Symposium on Reliable Distributed Systems Proceedings Start page 299 End page 309 Total pages 11 Publisher IEEE Place of publication Piscataway, N.J. Keyword(s) adversarial attack Computer Science Computer Science, Hardware & Architecture Computer Science, Information Systems Computer Science, Theory & Methods expert trajectory non-catastrophic reinforcement learning reward function Science & Technology Technology CORE2020 A ISBN 9781665438193 ISSN 1060-9857 2575-8462 Language eng DOI 10.1109/SRDS53918.2021.00037 HERDC Research category E1 Full written paper - refereed Persistent URL http://hdl.handle.net/10536/DRO/DU:30162030 Document type: Conference Paper Collections: Faculty of Science, Engineering and Built Environment School of Information Technology Related Links Link Description Connect to published version Go to link with your DU access privileges   Connect to Elements publication management system Go to link with your DU access privileges     Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved. Versions Version Filter Type Thu, 27 Jan 2022, 10:26:59 EST Thu, 27 Jan 2022, 14:34:42 EST Thu, 27 Jan 2022, 14:40:35 EST Sat, 12 Feb 2022, 01:30:27 EST Wed, 20 Apr 2022, 12:54:56 EST Wed, 20 Apr 2022, 16:48:00 EST Wed, 20 Apr 2022, 16:54:49 EST Filtered Full Citation counts:   Cited 0 times in TR Web of Science Cited 0 times in Scopus Search Google Scholar Access Statistics: 25 Abstract Views, 1 File Downloads  -  Detailed Statistics Created: Thu, 27 Jan 2022, 10:26:59 EST