Detecting Adversarial Directions in Deep Reinforcement Learning to Make Robust Decisions. (arXiv:2306.05873v1 [cs.LG])

Learning in MDPs with highly complex state representations is currently
possible due to multiple advancements in reinforcement learning algorithm
design. However, this incline in complexity, and furthermore the increase in
the dimensions of the observation came at the cost of volatility that can be
taken advantage of via adversarial attacks (i.e. moving along worst-case
directions in the observation space). To solve this policy instability problem
we propose a novel method to detect the presence of these non-robust directions
via local …

adversarial algorithm complexity cost design state taken volatility