Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defenses

1 code implementation • 16 Jun 2021 • Buse G. A. Tekgul, Shelly Wang, Samuel Marchal, N. Asokan

Via an extensive evaluation using three Atari 2600 games, we show that our attacks are effective, as they fully degrade the performance of three different DRL agents (up to 100%, even when the $l_\infty$ bound on the perturbation is as small as 0. 01).

Atari Games reinforcement-learning +1