mlsanityData to 7 Oct 2026

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

arXiv 2409.10171 ↗First posted 16 Sep 2024eess.SY cs.LG cs.SYcited by 6

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 10 of its 27 references that are in the map. First posted on arXiv 16 Sep 2024.

Builds on

10 of 27 references.

References · 10

  1. 2017On Kernelized Multi-armed Banditscited by 348
  2. 2017Cautious Model Predictive Control using Gaussian Process Regressioncited by 91
  3. 2019Safe Reinforcement Learning Using Robust MPCcited by 72
  4. 2021Practical and Rigorous Uncertainty Bounds for Gaussian Process Regressioncited by 49
  5. 2016Safe Learning of Regions of Attraction for Uncertain, Nonlinear Systems with Gaussian Processescited by 38
  6. 2019Performance-oriented model learning for data-driven MPC designcited by 22
  7. 2021Gaussian Process Uniform Error Bounds with Unknown Hyperparameters for Safety-Critical Applicationscited by 17
  8. 2024Stability-informed Bayesian Optimization for MPC Cost Function Learningcited by 8
  9. 2022Safe Bayesian Optimization using Interior-Point Methods -- Applied to Personalized Insulin Dose Guidancecited by 7
  10. 2024Learning Model Predictive Control Parameters via Bayesian Optimization for Battery Fast Chargingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 3; 2026: 1.

6 papers.

  1. 2024Time-Series-Informed Closed-loop Learning for Sequential Decision Making and Controlcited by 1
  2. 2025Exploiting Prior Knowledge in Preferential Learning of Individualized Autonomous Vehicle Driving Stylescited by 1
  3. 2025A Hierarchical Surrogate Model for Efficient Multi-Task Parameter Learning in Closed-Loop Controlcited by 1
  4. 2024Safe Learning-Based Optimization of Model Predictive Control: Application to Battery Fast-Chargingcited by 0
  5. 2025High-Dimensional Surrogate Modeling for Closed-Loop Learning of Neural-Network-Parameterized Model Predictive Controlcited by 0
  6. 2026Efficient Controller Learning from Human Preferences and Numerical Data Via Multi-Modal Surrogate Modelscited by 0