Towards Robust Deep Reinforcement Learning against Environmental State Perturbation

-- Adversarial attacks and robustness in Deep Reinforcement Learning (DRL) have been widely studied in various threat models; however, few consider environmental state perturbations, which are natural in embodied scenarios. T o improve the robustness of DRL agents, we formulate the problem of environmental state perturbation, introducing a preliminary non-targeted attack method as a calibration adversary, and then propose a defense framework, named Boosted Adversarial Training (BA T), which first tunes the agents via supervised learning to avoid catastrophic failure and subsequently adversarially trains the agent with reinforcement learning. Extensive experimental results substantiate the vulnerability of mainstream agents under environmental state perturbations and the effectiveness of our proposed attack. The defense results demonstrate that while existing robust reinforcement learning algorithms may not be suitable, our BA T framework can significantly enhance the robustness of agents against environmental state perturbations across various situations. The safety and robustness of Deep Reinforcement Learning (DRL) have been receiving increasing attention and have been studied in various domains, such as perturbation on the observation [1], [2], [3], [4] or the action [5], data poisoning [6], [7], adversarial policies [8], and multi-agent reinforcement learning [9], [10]. However, few works focus on the environmental robustness of the agent, which may be crucial for further applying DRL to robotic applications. In application, robots may be deployed in various environments that are different from the training one, with either unconscious or even malicious perturbations, such as placing or moving task-irrelevant objects. The limitations ensure the alignment between the problem we studied and robotic application scenarios in reality, where the perturbation is practical and corresponding attacks are realizable.