Performance evaluation in online approximation based control: methods and pitfalls

Analyzes the evaluation of approximation accuracy in online applications. In particular, it is first shown that the most commonly used performance evaluation method (e.g., analysis of training or tracking error) is not in itself sufficient to demonstrate proper function approximation. In spite of this, many articles use tracking (training) errors as the means to claim successful function approximation. This article presents two alternative methods for the online evaluation of approximation accuracy