paper-with-me

Papers

Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations

2020-03-19 · NeurIPS 2020 12 · Huan Zhang, Hongge Chen, Chaowei Xiao, Bo Li, Mingyan Liu, Duane Boning, Cho-Jui Hsieh

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.

📄 PDF Abstract BibTeX arXiv:2003.08938

Code (4)

chenhongge/StateAdvDRL 공식 구현 paddle
chenhongge/SA_DQN pytorch
huanzhang12/ATLA_robust_RL pytorch
huanzhang12/sa_ppo pytorch

Tasks

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Entropy Regularization 설명 없음
PPO Proximal Policy Optimization, or PPO, is a policy gradient method for reinforcement learning. The motivation was to have an algorithm with the data efficiency and reliable…
Experience Replay Experience Replay is a replay memory technique used in reinforcement learning where we store the agent’s experiences at each time-step, $e\_{t} = \left(s\_{t}, a\_{t}, r\_{t},…
Weight Decay 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…
Adam 설명 없음
Batch Normalization 설명 없음

Similar Papers 제목 키워드 기반

RoMFAC: A robust mean-field actor-critic reinforcement learning against adversarial perturbations on states

2022-05-15 · Ziyuan Zhou, Guanjun Liu

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

2019-05-25 · ICLR 2020 1 · Adam Gleave, Michael Dennis, Cody Wild, Neel Kant 외

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

2024-10-04 · Tung M. Luu, Thanh Nguyen, Tee Joshua Tian Jin, Sungwoon Kim 외

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+1

Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defenses

2021-06-16 · Buse G. A. Tekgul, Shelly Wang, Samuel Marchal, N. Asokan

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

2021-09-29 · Ezgi Korkmaz

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)