Learning practically stabilizing output-feedback nonlinear controllers

Abstract

This paper addresses the problem of learning an output-feedback surrogate controller offline that approximates a given, possibly computationally expensive, nonlinear controller-observer pair. The surrogate is modeled as a recurrent dynamical system and is trained to imitate closed-loop input/output trajectories generated by the given controller. Beyond imitation accuracy, the offline training problem promotes input-to-state practical stability by incorporating estimated state trajectories to learn a candidate Lyapunov function. The approach is validated on a nonlinear continuous stirred tank reactor, where constraint satisfaction and practical stability are assessed through a probabilistic validation approach. The numerical results highlight the benefit of jointly learning the Lyapunov function by comparing against an imitation-only baseline.