Optimizing Knowledge Component Learning Using a Dynamic Structural Model of Practice

This paper presents a generalized scheme for modeling learning in simple and more complex tasks, and shows how such a model can be applied to optimizing conditions of practice to maximize some desired performance. To enable this optimal allocation of lesson time, this paper describes how to quantify the preferences of students using utility functions that can be maximized. This conventional game theoretic approach is enabled by specifying a mathematical model that allows us to compute expected utility of various student choices to choose the choice with maximal expected utility. This method is applied to several educational decisions that can benefit from optimization.