A novel safety verification framework using forward and backward reachable tubes successfully determined whether model-based reinforcement learning controllers satisfied state constraints.
A novel safety verification framework using reachable set analysis can evaluate neural network-based reinforcement learning controllers and identify safe initial operating states.
Model-based reinforcement learning (RL) has emerged as a promising tool for developing controllers for real world systems (e.g., robotics, autonomous driving, etc.). However, real systems often have constraints imposed on their state space which must be satisfied to ensure the safety of the system and its environment. Developing a verification tool for RL algorithms is challenging because the non-linear structure of neural networks impedes analytical verification of such models or controllers. To this end, we present a novel safety verification framework for model-based RL controllers using reachable set analysis. The proposed frame-work can efficiently handle models and controllers which are represented using neural networks. Additionally, if a controller fails to satisfy the safety constraints in general, the proposed framework can also be used to identify the subset of initial states from which the controller can be safely executed.
Gupta et al. (2020) studied this question. A novel safety verification framework using forward and backward reachable tubes successfully determined whether model-based reinforcement learning controllers satisfied state constraints.