Safety Verification of Model Based Reinforcement Learning Controllers

akshita gupta, Inseok Hwang

Keywords: Reachable set, state constraints, safety verification, model-based reinforcement learning

Abstract: 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 framework 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.

One-sentence Summary: Safety verification and determination of safe initial states for model-based reinforcement learning controllers.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2010.10740/code)

Reviewed Version (pdf): https://openreview.net/references/pdf?id=FNGJjM9TEb