Timezone: »

 
Poster
Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning
Yongyuan Liang · Yanchao Sun · Ruijie Zheng · Furong Huang

Wed Nov 30 02:00 PM -- 04:00 PM (PST) @ Hall J #437
in Poster Session 4 »

Recent studies reveal that a well-trained deep reinforcement learning (RL) policy can be particularly vulnerable to adversarial perturbations on input observations. Therefore, it is crucial to train RL agents that are robust against any attacks with a bounded budget. Existing robust training methods in deep RL either treat correlated steps separately, ignoring the robustness of long-term rewards, or train the agents and RL-based attacker together, doubling the computational burden and sample complexity of the training process. In this work, we propose a strong and efficient robust training framework for RL, named Worst-case-aware Robust RL (WocaR-RL) that directly estimates and optimizes the worst-case reward of a policy under bounded l_p attacks without requiring extra samples for learning an attacker. Experiments on multiple environments show that WocaR-RL achieves state-of-the-art performance under various strong attacks, and obtains significantly higher training efficiency than prior state-of-the-art robust training methods. The code of this work is available at https://github.com/umd-huang-lab/WocaR-RL.

Keywords: Reinforcement Learning · Adversarial Learning · robustness · Worst-case Aware
[ Paper]  [ Slides]  [ Poster]  [ OpenReview] 

Author Information

Yongyuan Liang (SUN YAT-SEN UNIVERSITY)
Yanchao Sun (University of Maryland, College Park)
Ruijie Zheng (University of Maryland, College Park)
Furong Huang (University of Maryland)

More from the Same Authors