Machine learning and control engineering: The model-free case

TL;DR

This paper advocates for Model-Free Control (MFC) as a simple, effective alternative to traditional ML methods like neural networks and reinforcement learning in control engineering, supported by laboratory experiments.

Contribution

It introduces MFC as a new, easy-to-implement control tool distinct from reinforcement learning, demonstrating its viability through experimental validation.

Findings

MFC is a practical alternative to ML in control engineering.

Laboratory experiments confirm MFC's effectiveness.

MFC simplifies control system implementation.

Abstract

This paper states that Model-Free Control (MFC), which must not be confused with Model-Free Reinforcement Learning, is a new tool for Machine Learning (ML). MFC is easy to implement and should be substituted in control engineering to ML via Artificial Neural Networks and/or Reinforcement Learning. A laboratory experiment, which was already investigated via today's ML techniques, is reported in order to confirm this viewpoint.