Designing predictive controllers towards optimal closed-loop performance while maintaining safety and stability is challenging. This work explores closed-loop learning for predictive control parameters under imperfect information while considering closed-loop stability. We employ constrained Bayesian optimization to learn a model predictive controller's (MPC) cost function parametrized as a feedforward neural network, optimizing closed-loop behavior as well as minimizing model-plant mismatch. Doing so offers a high degree of freedom and, thus, the opportunity for efficient and global optimization towards the desired and optimal closed-loop behavior. We extend this framework by stability constraints on the learned controller parameters, exploiting the optimal value function of the underlying MPC as a Lyapunov candidate. The effectiveness of the proposed approach is underlined in simulations, highlighting its performance and safety capabilities.
@article{arxiv.2404.12187,
title = {Stability-informed Bayesian Optimization for MPC Cost Function Learning},
author = {Sebastian Hirt and Maik Pfefferkorn and Ali Mesbah and Rolf Findeisen},
journal= {arXiv preprint arXiv:2404.12187},
year = {2024}
}