Online Robustness Training for Deep Reinforcement Learning
arxiv(2019)
摘要
In deep reinforcement learning (RL), adversarial attacks can trick an agent into unwanted states and disrupt training. We propose a system called Robust Student-DQN (RS-DQN), which permits online robustness training alongside Q networks, while preserving competitive performance. We show that RS-DQN can be combined with (i) state-of-the-art adversarial training and (ii) provably robust training to obtain an agent that is resilient to strong attacks during training and evaluation.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络