Adversarial Reinforcement Learning For Observer Design In Autonomous Systems Under Cyber Attacks

Abstract

Complex autonomous control systems are subjected to sensor failures, cyber-attacks, sensor noise, communication channel failures, etc. that introduce errors in the measurements. The corrupted information, if used for making decisions, can lead to degraded performance. We develop a framework for using adversarial deep reinforcement learning to design observer strategies that are robust to adversarial errors in information channels. We further show through simulation studies that the learned observation strategies perform remarkably well when the adversary's injected errors are bounded in some sense. We use neural network as function approximator in our studies with the understanding that any other suitable function approximating class can be used within our framework.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keygupta2018adversarial

Related papers

• Understanding Adversarial Attacks On Observations In Deep Reinforcement Learning (2021)0.00
• Defending Observation Attacks In Deep Reinforcement Learning Via Detection And Denoising (2022)0.00
• Regret-based Defense In Adversarial Reinforcement Learning (2023)0.00
• Observed Adversaries In Deep Reinforcement Learning (2022)0.00
• Online Robust Policy Learning In The Presence Of Unknown Adversaries (2018)0.00
• Learning To Cope With Adversarial Attacks (2019)0.00
• Improving Robustness Of Reinforcement Learning For Power System Control With Adversarial Training (2021)0.00
• Adversarial Policies: Attacking Deep Reinforcement Learning (2019)0.00