Evaluating Reinforcement Learning Safety and Trustworthiness in Cyber-Physical Systems

Abstract--Cyber-Physical Systems (CPS) often leverage Reinforcement Learning (RL) techniques to adapt dynamically to changing environments and optimize performance. However, it is challenging to construct safety cases for RL components. We therefore propose the SAFE-RL (Safety and Accountability Framework for Evaluating Reinforcement Learning) for supporting the development, validation, and safe deployment of RLbased CPS. We adopt a design science approach to construct the framework and demonstrate its use in three RL applications in small Uncrewed Aerial systems (sUAS). Reinforcement Learning (RL) has become a key enabler of self-adaptive behaviors in Cyber-Physical Systems (CPS). Each ASK node adapting to dynamic and uncertain environments, RL enhances shows an icon for its related trustworthiness dimensions.