Regret-based Defense In Adversarial Reinforcement Learning

Abstract

Deep Reinforcement Learning (DRL) policies have been shown to be vulnerable to small adversarial noise in observations. Such adversarial noise can have disastrous consequences in safety-critical environments. For instance, a self-driving car receiving adversarially perturbed sensory observations about nearby signs (e.g., a stop sign physically altered to be perceived as a speed limit sign) or objects (e.g., cars altered to be recognized as trees) can be fatal. Existing approaches for making RL algorithms robust to an observation-perturbing adversary have focused on reactive approaches that iteratively improve against adversarial examples generated at each iteration. While such approaches have been shown to provide improvements over regular RL methods, they are reactive and can fare significantly worse if certain categories of adversarial examples are not generated during training. To that end, we pursue a more proactive approach that relies on directly optimizing a well-studied robustn

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybelaire2023regret

Related papers

• Attacking And Defending Deep Reinforcement Learning Policies (2022)0.00
• Robust Deep Reinforcement Learning Against Adversarial Perturbations On State Observations (2020)0.00
• On Minimizing Adversarial Counterfactual Error In Adversarial RL (2024)0.60
• Adversary Agnostic Robust Deep Reinforcement Learning (2020)6.77
• Adversarial Policies: Attacking Deep Reinforcement Learning (2019)0.00
• Robust Reinforcement Learning On State Observations With Learned Optimal Adversary (2021)0.00
• Robust Deep Reinforcement Learning With Adaptive Adversarial Perturbations In Action Space (2024)6.20
• Defending Observation Attacks In Deep Reinforcement Learning Via Detection And Denoising (2022)0.00