Timezone: »

 
Poster
Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations
Huan Zhang · Hongge Chen · Chaowei Xiao · Bo Li · Mingyan Liu · Duane Boning · Cho-Jui Hsieh

Wed Dec 09 09:00 AM -- 11:00 AM (PST) @ Poster Session 3 #920

A deep reinforcement learning (DRL) agent observes its states through observations, which may contain natural measurement errors or adversarial noises. Since the observations deviate from the true states, they can mislead the agent into making suboptimal actions. Several works have shown this vulnerability via adversarial attacks, but how to improve the robustness of DRL under this setting has not been well studied. We show that naively applying existing techniques on improving robustness for classification tasks, like adversarial training, are ineffective for many RL tasks. We propose the state-adversarial Markov decision process (SA-MDP) to study the fundamental properties of this problem, and develop a theoretically principled policy regularization which can be applied to a large family of DRL algorithms, including deep deterministic policy gradient (DDPG), proximal policy optimization (PPO) and deep Q networks (DQN), for both discrete and continuous action control problems. We significantly improve the robustness of DDPG, PPO and DQN agents under a suite of strong white box adversarial attacks, including two new attacks of our own. Additionally, we find that a robust policy noticeably improves DRL performance in a number of environments.

Author Information

Huan Zhang (UCLA)
Hongge Chen (MIT)
Chaowei Xiao (University of Michigan, Ann Arbor)

I am Chaowei Xiao, a third year PhD student in CSE Department, University of Michigan, Ann Arbor. My advisor is Professor Mingyan Liu . I obtained my bachelor's degree in School of Software from Tsinghua University in 2015, advised by Professor Yunhao Liu, Professor Zheng Yang and Dr. Lei Yang. I was also a visiting student at UC Berkeley in 2018, advised by Professor Dawn Song and Professor Bo Li. My research interest includes adversarial machine learning.

Bo Li (UIUC)
Mingyan Liu (University of Michigan, Ann Arbor)

Mingyan Liu (M'00, SM'11, F'14) received her Ph.D. Degree in electrical engineering from the University of Maryland, College Park, in 2000. She is currently a professor with the Department of Electrical Engineering and Computer Science at the University of Michigan, Ann Arbor, and the Peter and Evelyn Fuss Chair of Electrical and Computer Engineering. Her research interests are in optimal resource allocation, performance modeling, sequential decision and learning theory, game theory and incentive mechanisms, with applications to large-scale networked systems, cybersecurity and cyber risk quantification. She has served on the editorial boards of IEEE/ACM Trans. Networking, IEEE Trans. Mobile Computing, and ACM Trans. Sensor Networks. She is a Fellow of the IEEE and a member of the ACM.

Duane Boning (Massachusetts Institute of Technology)
Cho-Jui Hsieh (UCLA)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors