Belief-enriched Pessimistic Q-learning Against Adversarial State Perturbations

Abstract

Reinforcement learning (RL) has achieved phenomenal success in various domains. However, its data-driven nature also introduces new vulnerabilities that can be exploited by malicious opponents. Recent work shows that a well-trained RL agent can be easily manipulated by strategically perturbing its state observations at the test stage. Existing solutions either introduce a regularization term to improve the smoothness of the trained policy against perturbations or alternatively train the agent's policy and the attacker's policy. However, the former does not provide sufficient protection against strong attacks, while the latter is computationally prohibitive for large environments. In this work, we propose a new robust RL algorithm for deriving a pessimistic policy to safeguard against an agent's uncertainty about true states. This approach is further enhanced with belief state inference and diffusion-based state purification to reduce uncertainty. Empirical results show that our approac

Stats

• citations0
• S2 citations—
• github stars5
• HF likes0
• heat score1.56
• arxiv keysun2024belief

Related papers

• Robust Reinforcement Learning On State Observations With Learned Optimal Adversary (2021)0.00
• Robust Deep Reinforcement Learning Against Adversarial Perturbations On State Observations (2020)0.00
• On The Perturbed States For Transformed Input-robust Reinforcement Learning (2024)0.00
• Optimistic Policy Learning Under Pessimistic Adversaries With Regret And Violation Guarantees (2026)0.00
• Adversarial Policies: Attacking Deep Reinforcement Learning (2019)0.00
• Robust Model-based Reinforcement Learning With An Adversarial Auxiliary Model (2024)0.00
• Regret-based Defense In Adversarial Reinforcement Learning (2023)0.00
• Adversary Agnostic Robust Deep Reinforcement Learning (2020)6.77