Realizable Continuous-Space Shields for Safe Reinforcement Learning

TL;DR

This paper introduces a novel continuous-space shield for safe reinforcement learning that guarantees safety in robotic applications by ensuring realizability and handling non-Markovian safety requirements.

Contribution

It presents the first realizability-based shielding method for continuous state and action spaces, enabling safe RL in practical robotic scenarios.

Findings

Successfully applied to navigation and multi-agent environments.

Guarantees safety without reducing policy success rate.

Verifies realizability for non-Markovian safety requirements.

Abstract

While Deep Reinforcement Learning (DRL) has achieved remarkable success across various domains, it remains vulnerable to occasional catastrophic failures without additional safeguards. An effective solution to prevent these failures is to use a shield that validates and adjusts the agent's actions to ensure compliance with a provided set of safety specifications. For real-world robotic domains, it is essential to define safety specifications over continuous state and action spaces to accurately account for system dynamics and compute new actions that minimally deviate from the agent's original decision. In this paper, we present the first shielding approach specifically designed to ensure the satisfaction of safety requirements in continuous state and action spaces, making it suitable for practical robotic applications. Our method builds upon realizability, an essential property that confirms the shield will always be able to generate a safe action for any state in the environment. We formally prove that realizability can be verified for stateful shields, enabling the incorporation of non-Markovian safety requirements, such as loop avoidance. Finally, we demonstrate the effectiveness of our approach in ensuring safety without compromising the policy's success rate by applying it to a navigation problem and a multi-agent particle environment.