Adversarial Policies: Attacking Deep Reinforcement Learning
Deep reinforcement learning (RL) policies are known to be vulnerable to adversarial perturbations to their observations, similar to adversarial examples for classifiers. However, an attacker is not usually able to directly modify another agent's observations. This might lead one to wonder: is it possible to attack an RL agent simply by choosing an adversarial policy acting in a multi-agent environment so as to create natural observations that are adversarial? We demonstrate the existence of adversarial policies in zero-sum games between simulated humanoid robots with proprioceptive observations, against state-of-the-art victims trained via self-play to be robust to opponents. The adversarial policies reliably win against the victims but generate seemingly random and uncoordinated behavior. We find that these policies are more successful in high-dimensional environments, and induce substantially different activations in the victim policy network than when the victim plays against a normal opponent. Videos are available at https://adversarialpolicies.github.io/.
Code (2)
Tasks
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Attacking and Defending Deep Reinforcement Learning Policies
Recent studies have shown that deep reinforcement learning (DRL) policies are vulnerable to adversarial attacks, which raise concerns about applications of DRL to safety-critical systems. In this work, we adopt a princip…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Less is More: A Stealthy and Efficient Adversarial Attack Method for DRL-based Autonomous Driving Policies
Despite significant advancements in deep reinforcement learning (DRL)-based autonomous driving policies, these policies still exhibit vulnerability to adversarial attacks. This vulnerability poses a formidable challenge …
Adversarial AttackAutonomous DrivingDeep Reinforcement LearningKnowledge-enhanced Black-box Attacks for Recommendations
Recent studies have shown that deep neural networks-based recommender systems are vulnerable to adversarial attacks, where attackers can inject carefully crafted fake user profiles (i.e., a set of items that fake users h…
AttributeDeep Reinforcement LearningRecommendation SystemsStrategically-timed State-Observation Attacks on Deep Reinforcement Learning Agents
Deep reinforcement learning (DRL) policies are vulnerable to the adversarial attack on their observations, which may mislead real-world RL agents to catastrophic failures. Several works have shown the effectiveness of t…
Adversarial Attackcontinuous-controlContinuous ControlDeep Reinforcement Learning+3Sparse Black-box Video Attack with Reinforcement Learning
Adversarial attacks on video recognition models have been explored recently. However, most existing works treat each video frame equally and ignore their temporal interactions. To overcome this drawback, a few methods tr…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Video Recognition