Playing the piano is a complex skill that builds upon gradual mastery of prerequisite skills. As having a human teacher is expensive and not always available, a recent paper on arXiv.org proposes a model that guides the learner through the process of learning by choosing the practice method that has the highest expected utility.
It focuses on practicing one or several aspects or modes of the complex skill by reducing the complexity of the overall task. For instance, if pitch correctness is the target, the model allows the learner to play as slowly as they want. Besides practice organization, the task can be changed as well (like substituting every note to one single pitch to improve timing). A Gaussian Process (GP) is trained to represent the utility of practice modes. A simulated learner environment illustrates the application of the model and provides researchers with insights about how to shape future human learner studies.
A typical part of learning to play the piano is the progression through a series of practice units that focus on individual dimensions of the skill, such as hand coordination, correct posture, or correct timing. Ideally, a focus on a particular practice method should be made in a way to maximize the learner’s progress in learning to play the piano. Because we each learn differently, and because there are many choices for possible piano practice tasks and methods, the set of practice tasks should be dynamically adapted to the human learner. However, having a human teacher guide individual practice is not always feasible since it is time consuming, expensive, and not always available. Instead, we suggest to optimize in the space of practice methods, the so-called practice modes. The proposed optimization process takes into account the skills of the individual learner and their history of learning. In this work we present a modeling framework to guide the human learner through the learning process by choosing practice modes that have the highest expected utility (i.e., improvement in piano playing skill). To this end, we propose a human learner utility model based on a Gaussian process, and exemplify the model training and its application for practice scaffolding on an example of simulated human learners.
Research paper: Moringen, A., Rüttgers, S., Zintgraf, L., Friedman, J., and Ritter, H., “Optimizing piano practice with a utility-based scaffold”, 2021. Link: https://arxiv.org/abs/2106.12937