The Student Model of the LEAP Intelligent Tutoring System

LEAP is a coached practice environment that optimizes the learning process by maintaining and consulting a detailed student model. LEAP calculates a student model score for every action, exercise, and topic the student tries, then uses the scores both to provide feedback to the student and to select topics, exercises and actions for the student to practice. Using the student model to focus practice means exercises can be realistic and complex instead of artificial and simple, thereby reducing problems of motivation and transfer, and increasing LEAP’s similarity to apprenticeship learning. To optimize learning, LEAP selects exercises relevant to the current instructional topic, and modifies the selected exercises to focus trainees’ effort. Within an exercise, trainees practice material they are currently attempting to learn, review material they have already learned, and observe material that they are not yet prepared to learn. The student model is updated after each pass through an exercise, enabling LEAP to continually refocus its instruction as trainees learn or forget.