Hamilton-Jacobi Reachability in Reinforcement Learning: A Survey

TL;DR

This survey reviews recent advances in Hamilton-Jacobi reachability methods integrated with reinforcement learning, highlighting scalable techniques for safety verification and policy improvement in high-dimensional systems.

Contribution

It provides a comprehensive overview of recent methods that enable scalable HJ reachability analysis within reinforcement learning frameworks for complex systems.

Findings

Recent methods improve scalability of HJ reachability analysis

HJ reachability enhances safety guarantees in RL policies

Applications include dynamic obstacle avoidance and vision-based control

Abstract

Recent literature has proposed approaches that learn control policies with high performance while maintaining safety guarantees. Synthesizing Hamilton-Jacobi (HJ) reachable sets has become an effective tool for verifying safety and supervising the training of reinforcement learning-based control policies for complex, high-dimensional systems. Previously, HJ reachability was restricted to verifying low-dimensional dynamical systems primarily because the computational complexity of the dynamic programming approach it relied on grows exponentially with the number of system states. In recent years, a litany of proposed methods addresses this limitation by computing the reachability value function simultaneously with learning control policies to scale HJ reachability analysis while still maintaining a reliable estimate of the true reachable set. These HJ reachability approximations are used to improve the safety, and even reward performance, of learned control policies and can solve challenging tasks such as those with dynamic obstacles and/or with lidar-based or vision-based observations. In this survey paper, we review the recent developments in the field of HJ reachability estimation in reinforcement learning that would provide a foundational basis for further research into reliability in high-dimensional systems.