Robust Deep Reinforcement Learning with Adversarial Attacks

Anay Pattanaik (University of Illinois at Urbana-Champaign), Zhenyi Tang (University of Illinois at Urbana-Champaign), Shuijing Liu (University of Illinois at Urbana-Champaign), Gautham Bommannan (University of Illinois at Urbana-Champaign), Girish Chowdhary (University of Illinois at Urbana-Champaign)

Abstract

This paper proposes adversarial attacks for Reinforcement Learning (RL). These attacks are then leveraged during training to improve the robustness of RL within robust control framework. We show that this adversarial training of DRL algorithms like Deep Double Q learning and Deep Deterministic Policy Gradients leads to significant increase in robustness to parameter variations for RL benchmarks such as Mountain Car and Hopper environment. Full paper is available at (https://arxiv.org/abs/1712.03632) [7].