Shielding Regular Safety Properties in Reinforcement Learning

Alex Goodall, Francesco Belardinelli

Keywords: Safe Reinforcement Learning, Model Checking, Shielding

Abstract: To deploy reinforcement learning (RL) systems in real-world scenarios we need to consider requirements such as safety and constraint compliance, rather than blindly maximizing for reward. In this paper we study RL with regular safety properties. We present a constrained problem based on the satisfaction of regular safety properties with high probability and we compare our setup to the some common constrained Markov decision processes (CMDP) settings. We also present a meta-algorithm with provable safety-guarantees, that can be used to shield the agent from violating the regular safety property during training and deployment. We demonstrate the effectiveness and scalability of our framework by evaluating our meta-algorithm in both the tabular and deep RL setting.

Primary Area: Reinforcement learning

Submission Number: 15393