Web: http://arxiv.org/abs/2106.05087

Jan. 13, 2022, 2:20 a.m. | Yanchao Sun, Ruijie Zheng, Yongyuan Liang, Furong Huang

cs.CR updates on arXiv.org arxiv.org

Evaluating the worst-case performance of a reinforcement learning (RL) agent
under the strongest/optimal adversarial perturbations on state observations
(within some constraints) is crucial for understanding the robustness of RL
agents. However, finding the optimal adversary is challenging, in terms of both
whether we can find the optimal attack and how efficiently we can find it.
Existing works on adversarial RL either use heuristics-based methods that may
not find the strongest adversary, or directly train an RL-based adversary by
treating the …

attacks evasion lg who

Head of Information Security

@ Canny | Remote

Information Technology Specialist (INFOSEC)

@ U.S. Securities & Exchange Commission | Washington, D.C.

Information Security Manager - $90K-$180K - MANAG002176

@ Sound Transit | Seattle, WA

Sr. Software Security Architect

@ SAS | Remote

Senior Incident Responder

@ CipherTechs, Inc. | Remote

Data Security DevOps Engineer Senior/Intermediate

@ University of Michigan - ITS | Ann Arbor, MI