敵対的攻撃を用いた頑健な深層強化学習
Robust Deep Reinforcement Learning with Adversarial Attacks
強化学習に対する敵対的攻撃を提案し、その攻撃を訓練中に用いることでパラメータ不確実性に対する深層強化学習の頑健性を向上させた論文。
著者: Anay Pattanaik, Zhenyi Tang, Shuijing Liu, Gautham Bommannan, Girish Chowdhary
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
This paper proposes adversarial attacks for Reinforcement Learning (RL) and then improves the robustness of Deep Reinforcement Learning algorithms (DRL) to parameter uncertainties with the help of these attacks. We show that even a naively engineered attack successfully degrades the performance of DRL algorithm. We further improve the attack using gradient information of an engineered loss function which leads to further degradation in performance. 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 Cart-pole, Mountain Car, Hopper and Half Cheetah environment.
