This paper presents an inverse optimal control approach to identify objective functions of human motion from motion capture measurements. We apply it to analyze human yoyo playing. Yoyo playing may seem easy to us to learn but it is a challenging problem from a mechanical point of view involving a hybrid dynamics model. We recorded vertical yoyo playing of humans measuring yoyo height and rotation angle as well as the corresponding hand motions. Results of inverse optimal control are presented showing a mixed criterion of cycle time and terms depending on yoyo and hand acceleration and velocity.