Adversarially Robust Policy Learning through Active Construction of Physically-Plausible Perturbations

Policy search methods in reinforcement learning have demonstrated success in scaling up to larger problem sizes beyond toy examples. However, deploying these methods on real robots remains challenging due to the large sample complexity required during learning and their vulnerability to malicious intervention. We introduce Adversarially Robust Policy Learning (ARPL), an algorithm that leverages active computation of physically-plausible adversarial examples during training to enable sample-efficient policy learning in the source domain and robust performance under both random and adversarial input perturbations. We evaluate ARPL on four continuous control tasks and show superior resilience to changes in physical environment dynamics parameters and environment state as compared to state-of-the-art robust policy learning methods.