Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL. (arXiv:2106.05087v3 [cs.LG] UPDATED)

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 …

arxiv attacks deep rl rl