We study black-box reward poisoning attacks against reinforcement learning
(RL), in which an adversary aims to manipulate the rewards to mislead a
sequence of RL agents with unknown algorithms to learn a nefarious policy in an
environment unknown to the adversary a priori. That is, our attack makes
minimum assumptions on the prior knowledge of the adversary: it has no initial
knowledge of the environment or the learner, and neither does it observe the
learner’s internal mechanism except for its performed actions. We design a
novel black-box attack, U2, that can provably achieve a near-matching
performance to the state-of-the-art white-box attack, demonstrating the
feasibility of reward poisoning even in the most challenging black-box setting.

By admin