Skip to content

Opening book details…

About this document

Data-Driven Model Predictive Control by hinsermu is a document available to read on EtoBox.

This document discusses using machine learning techniques to design model predictive control (MPC). It describes using machine learning to identify prediction models from data and then using reinforcement learning to learn the optimal MPC law directly from data. Specifically, it mentions using autoencoders or recurrent neural networks to identify nonlinear models, and Q-learning or policy gradient methods to learn the MPC policy. The goal is to design MPC systems from data using combined machine learning an

Author
hinsermu
Language
EN