Adversarial Robust Deep Reinforcement Learning Requires Redefining Robustness

2023-01-17 · Ezgi Korkmaz

Learning from raw high dimensional data via interaction with a given environment has been effectively achieved through the utilization of deep neural networks. Yet the observed degradation in policy performance caused by imperceptible worst-case policy dependent translations along high sensitivity directions (i.e. adversarial perturbations) raises concerns on the robustness of deep reinforcement learning policies. In our paper, we show that these high sensitivity directions do not lie only along particular worst-case directions, but rather are more abundant in the deep neural policy landscape and can be found via more natural means in a black-box setting. Furthermore, we show that vanilla training techniques intriguingly result in learning more robust policies compared to the policies learnt via the state-of-the-art adversarial training techniques. We believe our work lays out intriguing properties of the deep reinforcement learning policy manifold and our results can help to build robust and generalizable deep reinforcement learning policies.

📄 PDF Abstract BibTeX arXiv:2301.07487

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Sensitivity

Focus on Hiders: Exploring Hidden Threats for Enhancing Adversarial Training

2023-12-12 · CVPR 2024 1 · Qian Li, Yuxiao Hu, Yinpeng Dong, Dongxiao Zhang 외

Adversarial training is often formulated as a min-max problem, however, concentrating only on the worst adversarial examples causes alternating repetitive confusion of the model, i.e., previously defended or correctly cl…

Robust Adversarial Reinforcement Learning via Bounded Rationality Curricula

2023-11-03 · Aryaman Reddi, Maximilian Tölle, Jan Peters, Georgia Chalvatzaki 외

Robustness against adversarial attacks and distribution shifts is a long-standing goal of Reinforcement Learning (RL). To this end, Robust Adversarial Reinforcement Learning (RARL) trains a protagonist against destabiliz…

MuJoCo reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Non-Robust Feature Mapping in Deep Reinforcement Learning

2021-06-18 · ICML Workshop AML 2021 7 · Ezgi Korkmaz

Adversarial perturbations to state observations can dramatically degrade the performance of deep reinforcement learning policies, and thus raise concerns regarding the robustness of deep reinforcement learning agents. A …

Atari Games Deep Reinforcement Learning reinforcement-learning Reinforcement Learning+1

BARReL: Bottleneck Attention for Adversarial Robustness in Vision-Based Reinforcement Learning

2022-08-22 · Eugene Bykovets, Yannick Metz, Mennatallah El-Assady, Daniel A. Keim 외

Robustness to adversarial perturbations has been explored in many areas of computer vision. This robustness is particularly relevant in vision-based reinforcement learning, as the actions of autonomous agents might be sa…

Adversarial Robustness reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Enhancing the Robustness of QMIX against State-adversarial Attacks

2023-07-03 · Weiran Guo, Guanjun Liu, Ziyuan Zhou, Ling Wang 외

Deep reinforcement learning (DRL) performance is generally impacted by state-adversarial attacks, a perturbation applied to an agent's observation. Most recent research has concentrated on robust single-agent reinforceme…

Deep Reinforcement Learning Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning