Presents a control and learning architecture for humanoid robots designed for acquiring movement skills in the context of imitation learning. Multiple levels of movement abstraction occur across the hierarchical structure of the architecture, finally leading to the representation of movement sequences within a probabilistic framework. As its substrate, the framework uses the notion of visuo-motor primitives, modules capable of recognizing as well as executing similar movements. This notion is heavily motivated by the neuroscience evidence for motor primitives and mirror neurons. Experimental results from an implementation of the architecture are presented involving learning and representation of demonstrated movement sequences from synthetic as well as real human movement data.