Enhancing Robustness in Deep Reinforcement Learning: A Lyapunov Exponent Approach Rory Young Nicolas Pugeault School of Computing Science University of Glasgow

Deep reinforcement learning agents achieve state-of-the-art performance in a wide range of simulated control tasks. However, successful applications to real-world problems remain limited. One reason for this dichotomy is because the learnt policies are not robust to observation noise or adversarial attacks. In this paper, we investigate the robustness of deep RL policies to a single small state perturbation in deterministic continuous control tasks.