Don't Throw Your Old Policies Away: Knowledge-based Policy Recycling Protects Against Adversarial Attacks

Yaqi Xie, Chen Yu, Harold Soh

Keywords: Domain Knowledge, Knowledge Representation, Representation Learning, Policy Ensemble

TL;DR: Incorporating domain-knowledge over auxiliary tasks enhances deep reinforcement policy robustness against adversarial attacks in both Atari games and a high dimensional Robot Food Court environment.

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.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning