Robust Deep Reinforcement Learning With Adaptive Adversarial Perturbations In Action Space

Abstract

Deep reinforcement learning (DRL) algorithms can suffer from modeling errors between the simulation and the real world. Many studies use adversarial learning to generate perturbation during training process to model the discrepancy and improve the robustness of DRL. However, most of these approaches use a fixed parameter to control the intensity of the adversarial perturbation, which can lead to a trade-off between average performance and robustness. In fact, finding the optimal parameter of the perturbation is challenging, as excessive perturbations may destabilize training and compromise agent performance, while insufficient perturbations may not impart enough information to enhance robustness. To keep the training stable while improving robustness, we propose a simple but effective method, namely, Adaptive Adversarial Perturbation (A2P), which can dynamically select appropriate adversarial perturbations for each sample. Specifically, we propose an adaptive adversarial coefficient fr

Stats

• citations4
• S2 citations—
• github stars2
• HF likes0
• heat score6.20
• arxiv keyliu2024robust

Related papers

• Robust Deep Reinforcement Learning Against Adversarial Perturbations On State Observations (2020)0.00
• Robust Deep Reinforcement Learning Through Adversarial Attacks And Training : A Survey (2024)0.00
• Robust Reinforcement Learning On State Observations With Learned Optimal Adversary (2021)0.00
• Regret-based Defense In Adversarial Reinforcement Learning (2023)0.00
• Real-time Adversarial Perturbations Against Deep Reinforcement Learning Policies: Attacks And Defenses (2021)0.00
• Robust Deep Reinforcement Learning Through Adversarial Loss (2020)0.00
• Adversary Agnostic Robust Deep Reinforcement Learning (2020)6.77
• Robust Model-based Reinforcement Learning With An Adversarial Auxiliary Model (2024)0.00