Machine learning and control engineering: The model-free case
This work targets control engineering by suggesting a paradigm shift from current ML techniques, but it appears incremental as it builds on existing control concepts without broad validation.
The paper proposes Model-Free Control (MFC) as a new tool for machine learning in control engineering, claiming it is easy to implement and should replace existing ML methods like neural networks and reinforcement learning, with a laboratory experiment used to support this view.
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.