An efficient data-driven control algorithm with experimental validation

What is it about?

This paper proposes the combination of two model-free controller tuning techniques, namely linear Virtual Reference Feedback Tuning (VRFT) and nonlinear state-feedback Q-learning. Our new mixed VRFT-Q learning approach employs neural networks and is solves the reference trajectory tracking problems defined as optimization problems.

Featured Image

Why is it important?

This can be of large importance for many applications as extensive simulation results for a representative nonlinear system are included.

Perspectives