Certifying Hamilton-Jacobi Reachability Learned via Reinforcement Learning

Prashant Solanki, Isabelle El-Hajj, Jasper J. van Beers +2

We present a framework to \emph{certify} Hamilton--Jacobi (HJ) reachability learned by reinforcement learning (RL). Building on a discounted initial time \emph{travel-cost} formula…