Improving Robustness Of Deep Reinforcement Learning Agents: Environment Attack Based On The Critic Network

Abstract

To improve policy robustness of deep reinforcement learning agents, a line of recent works focus on producing disturbances of the environment. Existing approaches of the literature to generate meaningful disturbances of the environment are adversarial reinforcement learning methods. These methods set the problem as a two-player game between the protagonist agent, which learns to perform a task in an environment, and the adversary agent, which learns to disturb the protagonist via modifications of the considered environment. Both protagonist and adversary are trained with deep reinforcement learning algorithms. Alternatively, we propose in this paper to build on gradient-based adversarial attacks, usually used for classification tasks for instance, that we apply on the critic network of the protagonist to identify efficient disturbances of the environment. Rather than learning an attacker policy, which usually reveals as very complex and unstable, we leverage the knowledge of the critic

Stats

• citations5
• S2 citations—
• github stars0
• HF likes0
• heat score5.84
• arxiv keyschott2021improving

Related papers

• Adversarial Policies: Attacking Deep Reinforcement Learning (2019)0.00
• Investigating Vulnerabilities Of Deep Neural Policies (2021)0.00
• Attacking And Defending Deep Reinforcement Learning Policies (2022)0.00
• Toward Evaluating Robustness Of Reinforcement Learning With Adversarial Policy (2023)4.52
• Rethinking Adversarial Attacks In Reinforcement Learning From Policy Distribution Perspective (2025)5.84
• 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
• Observed Adversaries In Deep Reinforcement Learning (2022)0.00