Shields for Safe Reinforcement Learning

Reinforcement learning (RL) is a prominent machine learning technique used to optimize an agent’s performance in potentially unknown environments. Despite its popularity and success, RL lacks safety guarantees, both during the learning phase and deployment. This paper reviews a runtime enforcement method called shielding that ensures provable safety for RL. We describe the underlying models, the types of guarantees that can be delivered, and the process of computing shields. Furthermore, we describe several techniques for integrating shields into RL, discuss the advantages and potential drawbacks of this integration, and highlight the current challenges in shielded learning. Evaluating the advantages and potential drawbacks of shielding as a method for safe RL.