Online Robustness Training for Deep Reinforcement Learning

Authors: Marc Fischer, Matthew Mirman, Steven Stalder, Martin Vechev
Published: 2019-11-03 | Updated: 2019-11-22

Source: https://arxiv.org/abs/1911.00887

PDF: https://arxiv.org/pdf/1911.00887

Labels Predicted by AI

学習の改善 ポイズニング 知識の蒸留

Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.

Abstract

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.