Safe and Stable Closed-Loop Learning for Neural-Network-Supported Model Predictive Control

TL;DR

This paper introduces a Bayesian optimization approach for safe, stable, and flexible learning of neural-network-parametrized predictive controllers in closed-loop systems, ensuring long-term performance and safety guarantees.

Contribution

It presents a novel method integrating neural network parametrization with Bayesian optimization to guarantee safety and stability in closed-loop predictive control.

Findings

Achieves probabilistic safety guarantees in control learning.

Enhances closed-loop performance through neural network parametrization.

Demonstrates effectiveness via numerical example.

Abstract

Safe learning of control policies remains challenging, both in optimal control and reinforcement learning. In this article, we consider safe learning of parametrized predictive controllers that operate with incomplete information about the underlying process. To this end, we employ Bayesian optimization for learning the best parameters from closed-loop data. Our method focuses on the system's overall long-term performance in closed-loop while keeping it safe and stable. Specifically, we parametrize the stage cost function of an MPC using a feedforward neural network. This allows for a high degree of flexibility, enabling the system to achieve a better closed-loop performance with respect to a superordinate measure. However, this flexibility also necessitates safety measures, especially with respect to closed-loop stability. To this end, we explicitly incorporated stability information in the Bayesian-optimization-based learning procedure, thereby achieving rigorous probabilistic safety guarantees. The proposed approach is illustrated using a numeric example.