Observed Adversaries In Deep Reinforcement Learning

Abstract

In this work, we point out the problem of observed adversaries for deep policies. Specifically, recent work has shown that deep reinforcement learning is susceptible to adversarial attacks where an observed adversary acts under environmental constraints to invoke natural but adversarial observations. This setting is particularly relevant for HRI since HRI-related robots are expected to perform their tasks around and with other agents. In this work, we demonstrate that this effect persists even with low-dimensional observations. We further show that these adversarial attacks transfer across victims, which potentially allows malicious attackers to train an adversary without access to the target victim.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylim2022observed

Related papers

• Adversarial Policies: Attacking Deep Reinforcement Learning (2019)0.00
• 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
• Snooping Attacks On Deep Reinforcement Learning (2019)2.26
• Robust Deep Reinforcement Learning Against Adversarial Behavior Manipulation (2024)0.00
• Robust Deep Reinforcement Learning Through Adversarial Attacks And Training : A Survey (2024)0.00
• Robust Deep Reinforcement Learning Against Adversarial Perturbations On State Observations (2020)0.00
• Online Robust Policy Learning In The Presence Of Unknown Adversaries (2018)0.00