A Lyapunov-based Approach to Safe Reinforcement Learning

TL;DR

This paper introduces a Lyapunov-based method to ensure safety in reinforcement learning by incorporating constraints, enabling agents to learn effectively while avoiding unsafe actions during training and deployment.

Contribution

The paper develops a novel Lyapunov function framework for safe RL, transforming standard algorithms into safety-aware versions within the CMDP setting.

Findings

The Lyapunov approach guarantees global safety during training.

The method outperforms baselines in balancing safety and performance.

Effective in various CMDP planning tasks.

Abstract

In many real-world reinforcement learning (RL) problems, besides optimizing the main objective function, an agent must concurrently avoid violating a number of constraints. In particular, besides optimizing performance it is crucial to guarantee the safety of an agent during training as well as deployment (e.g. a robot should avoid taking actions - exploratory or not - which irrevocably harm its hardware). To incorporate safety in RL, we derive algorithms under the framework of constrained Markov decision problems (CMDPs), an extension of the standard Markov decision problems (MDPs) augmented with constraints on expected cumulative costs. Our approach hinges on a novel \emph{Lyapunov} method. We define and present a method for constructing Lyapunov functions, which provide an effective way to guarantee the global safety of a behavior policy during training via a set of local, linear constraints. Leveraging these theoretical underpinnings, we show how to use the Lyapunov approach to systematically transform dynamic programming (DP) and RL algorithms into their safe counterparts. To illustrate their effectiveness, we evaluate these algorithms in several CMDP planning and decision-making tasks on a safety benchmark domain. Our results show that our proposed method significantly outperforms existing baselines in balancing constraint satisfaction and performance.