no code implementations • ICLR 2020 • Tsui-Wei Weng, Krishnamurthy (Dj) Dvijotham*, Jonathan Uesato*, Kai Xiao*, Sven Gowal*, Robert Stanforth*, Pushmeet Kohli
Deep reinforcement learning has achieved great success in many previously difficult reinforcement learning tasks, yet recent studies show that deep RL agents are also unavoidably susceptible to adversarial perturbations, similar to deep neural networks in classification tasks.