Robust Deep Reinforcement Learning Against Adversarial Perturbations On State Observations

Abstract

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

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhang2020robust

Related papers

• Robust Reinforcement Learning On State Observations With Learned Optimal Adversary (2021)0.00
• Adversary Agnostic Robust Deep Reinforcement Learning (2020)6.77
• Regret-based Defense In Adversarial Reinforcement Learning (2023)0.00
• Robust Deep Reinforcement Learning With Adaptive Adversarial Perturbations In Action Space (2024)6.20
• Robust Deep Reinforcement Learning Through Adversarial Attacks And Training : A Survey (2024)0.00
• Belief-enriched Pessimistic Q-learning Against Adversarial State Perturbations (2024)1.56
• Adversarial Policies: Attacking Deep Reinforcement Learning (2019)0.00
• Exploring The Training Robustness Of Distributional Reinforcement Learning Against Noisy State Observations (2021)0.00