Although robot-assisted rehabilitation regimens are as effective, functionally, as conventional therapies, they still lack features to increase patients' engagement in the regimen. Providing rehabilitation tasks at a "desirable difficulty" is one of the ways to address this issue and increase the motivation of a patient to continue with the therapy program. Then the problem is to design a system that is capable of estimating the user's desirable difficulty, and ultimately, modifying the task based on this prediction. In this paper we compared the performance of three machine learning algorithms in predicting a user's desirable difficulty during a typical reaching motion rehabilitation task. Different levels of error amplification were used as different levels of task difficulty. We explored the usefulness of using participants' motor performance and physiological signals during the reaching task in prediction of their desirable difficulties. Results showed that a Neural Network approach gives higher prediction accuracy in comparison with models based on k-Nearest Neighbor and Discriminant Analysis methods.