Don't Throw Your Old Policies Away: Knowledge-based Policy Recycling Protects Against Adversarial Attacks
Lists
Only you see this
Abstract
Recent work has shown that Deep Reinforcement Learning (DRL) is vulnerable to adversarial attacks, in which minor perturbations of input signals cause agents to behave inappropriately and unexpectedly. Humans, on the other hand, appear robust to these particular sorts of input variations. We posit that this part of robustness stems from accumulated knowledge about the world. In this work, we propose to leverage prior knowledge to defend against adversarial attacks in RL settings using a framework we call Knowledge-based Policy Recycling (KPR). Different from previous defense methods such as adversarial training and robust learning, KPR incorporates domain knowledge over a set of auxiliary tasks policies and learns relations among them from interactions with the environment via a Graph Neural Network (GNN). KPR can use any relevant policy as an auxiliary policy and, importantly, does not assume access or information regarding the adversarial attack. Empirically, KPR results in policies that are more robust to various adversarial attacks in Atari games and a simulated Robot Foodcourt environment.
BibTeX
@inproceedings{xie2023don,
author = {Yaqi Xie and Chen Yu and Harold Soh},
title = {{Don't Throw Your Old Policies Away: Knowledge-based Policy Recycling Protects Against Adversarial Attacks}},
booktitle = {International Conference on Learning Representations},
year = {2023},
url = {https://openreview.net/forum?id=oCx90Ezdox_},
}Loading related content...