Robust Policy Gradient against Strong Data Corruption

Understand

We study the problem of robust reinforcement learning under adversarial corruption on both rewards and transitions.

• Our attack model assumes an \textit{adaptive} adversary who can arbitrarily corrupt the reward and transition at every step within an episode, for at most $\epsilon$-fraction of the learning episodes.
• Our attack model is strictly stronger than those considered in prior works.
• Our first result shows that no algorithm can find a better than $O(\epsilon)$-optimal policy under our attack model.