Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations
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 existing approaches on improving the robustness of DRL under this setting have limited success and lack for theoretical principles. We show that naively applying existing techniques on improving robustness for classification tasks, like adversarial training, is 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 proximal policy optimization (PPO), deep deterministic policy gradient (DDPG) and deep Q networks (DQN), for both discrete and continuous action control problems. We significantly improve the robustness of PPO, DDPG and DQN agents under a suite of strong white box adversarial attacks, including new attacks of our own. Additionally, we find that a robust policy noticeably improves DRL performance even without an adversary in a number of environments. Our code is available at https://github.com/chenhongge/StateAdvDRL.
Code (4)
Tasks
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
RoMFAC: A robust mean-field actor-critic reinforcement learning against adversarial perturbations on states
Multi-agent deep reinforcement learning makes optimal decisions dependent on system states observed by agents, but any uncertainty on the observations may mislead agents to take wrong actions. The Mean-Field Actor-Critic…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)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 direct…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Mitigating Adversarial Perturbations for Deep Reinforcement Learning via Vector Quantization
Recent studies reveal that well-performing reinforcement learning (RL) agents in training often lack resilience against adversarial perturbations during deployment. This highlights the importance of building a robust age…
Deep Reinforcement LearningQuantizationreinforcement-learningReinforcement Learning+1Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defenses
Deep reinforcement learning (DRL) is vulnerable to adversarial perturbations. Adversaries can mislead the policies of DRL agents by perturbing the state of the environment observed by the agents. Existing attacks are fea…
Atari GamesDeep Reinforcement Learningreinforcement-learningReinforcement Learning (RL)Assessing Deep Reinforcement Learning Policies via Natural Corruptions at the Edge of Imperceptibility
Deep reinforcement learning algorithms have recently achieved significant success in learning high-performing policies from purely visual observations. The ability to perform end-to-end learning from raw high dimensional…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)