Aug 3, 2023 · (Economic) nonlinear model predictive control ((e)NMPC) requires dynamic models that are sufficiently accurate and computationally tractable.

(Economic) nonlinear model predictive control ((e)NMPC) requires dynamic system models that are sufficiently accurate in all relevant state-space regions.

Aug 3, 2023 · We compare the controller performance to that of MPCs utilizing models trained by the prevailing maximum prediction accuracy paradigm, and model ...

Abstract:(Economic) nonlinear model predictive control ((e)NMPC) requires dynamic models that are sufficiently accurate and computationally tractable.

Reinforcement learning of Koopman models enhances performance in economic nonlinear model predictive control.

This paper introduces a new approach that combines machine learning and control theory to develop better control systems for complex processes.

We present a method for end-to-end reinforcement learning of Koopman surrogate models for optimal performance as part of (e)NMPC. We apply our method to two ...

We present a method for end-to-end learning of Koopman surrogate models for optimal performance in control. Reinforcement Learning (RL).

Missing: Nonlinear | Show results with:Nonlinear

Another group of works is model-free, where control laws are learned out of data directly, e.g. reinforcement learning, adaptive dynamic programming, and ...