One embodiment of the invention disclosed herein provides techniques for controlling a movement training environment. A movement training system retrieves a movement object from a set of movement objects. The movement training system attains first motion capture data associated with a first user performing a movement based on the movement object. The movement training system generates a first articulable representation based on the first motion capture data. The movement training system compares at least one first joint position related to the first articulable representation with at least one second joint position related to a second articulable representation associated with the movement object. The movement training system calculates a first similarity score based on a difference between the at least one first joint position and the at least one second joint position.