Whatever Does Not Kill Deep Reinforcement Learning, Makes It Stronger release_rzi4py4p4fejvp6oiiiaxjc5ga

by Vahid Behzadan, Arslan Munir

Released as a article .

2017  

Abstract

Recent developments have established the vulnerability of deep Reinforcement Learning (RL) to policy manipulation attacks via adversarial perturbations. In this paper, we investigate the robustness and resilience of deep RL to training-time and test-time attacks. Through experimental results, we demonstrate that under noncontiguous training-time attacks, Deep Q-Network (DQN) agents can recover and adapt to the adversarial conditions by reactively adjusting the policy. Our results also show that policies learned under adversarial perturbations are more robust to test-time attacks. Furthermore, we compare the performance of ϵ-greedy and parameter-space noise exploration methods in terms of robustness and resilience against adversarial perturbations.
In text/plain format

Archived Files and Locations

application/pdf  208.2 kB
file_2ztnid3oknh45muahzfivxsnne
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2017-12-23
Version   v1
Language   en ?
arXiv  1712.09344v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 63a4712a-3835-4c83-b336-109861396dbe
API URL: JSON