Guoliang Fan

Guoliang Fan

Auto-generated profile, based on publicly available information

Guoliang Fan

Institute of Automation Chinese Academy of Sciences, CHINA

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 December 2022
Verified
Conference Paper
Open access
CGChen Gong
Chen Gong
ZYZhou Yang
Zhou Yang
YBYunpeng Bai
Yunpeng Bai
JSJieke Shi
Jieke Shi
ASArunesh Sinha
Arunesh Sinha
GFGuoliang Fan
Guoliang Fan
Recent years have witnessed great potential in applying Deep Reinforcement Learning (DRL) in various challenging applications, such as autonomous driving, nuclear fusion control, complex game playing, etc. However, recently researchers have revealed that deep reinforcement learning models are vulnerable to adversarial attacks: malicious attackers can train adversarial policies to tamper with the observations of a well-trained victim agent, the latter of which fails dramatically when faced with such an attack. Understanding and improving the adversarial robustness of deep reinforcement learning is of great importance in enhancing the quality and reliability of a wide range of DRL-enabled systems. In this paper, we develop curiosity-driven and victim-aware adversarial policy training, a novel method that can more effectively exploit the defects of victim agents. To be victim-aware, we build a surrogate network that can approximate the state-value function of a black-box victim to collect the victim’s information. Then we propose a curiosity-driven approach, which encourages an adversarial policy to utilize the information from the hidden layer of the surrogate network to exploit the vulnerability of victims efficiently. Extensive experiments demonstrate that our proposed method outperforms or achieves a similar level of performance as the current state-of-the-art across multiple environments. We perform an ablation study to emphasize the benefits of utilizing the approximated victim information. Further analysis suggests that our method is harder to defend against a commonly used defensive strategy, which calls attention to more effective protection on the systems using DRL.