Bounded Myopic Adversaries for Deep Reinforcement Learning Agents

Ezgi Korkmaz, Henrik Sandberg, Gyorgy Dan

Keywords: deep reinforcement learning, adversarial

Abstract: Adversarial attacks against deep neural networks have been widely studied. Adversarial examples for deep reinforcement learning (DeepRL) have significant security implications, due to the deployment of these algorithms in many application domains. In this work we formalize an optimal myopic adversary for deep reinforcement learning agents. Our adversary attempts to find a bounded perturbation of the state which minimizes the value of the action taken by the agent. We show with experiments in various games in the Atari environment that our attack formulation achieves significantly larger impact as compared to the current state-of-the-art. Furthermore, this enables us to lower the bounds by several orders of magnitude on the perturbation needed to efficiently achieve significant impacts on DeepRL agents.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=dkuJMHfeId