A conceptual model for game based intelligent tutoring systems

School of EducationCharles Sturt UniversityIn order to build intelligent tutoring agents within games-based learning environments,practitioners must understand the three conceptual models used within Intelligent TutoringSystems (ITS): the expert or domain model, the student model, and the instructional model.This paper investigates the inter-relationship between these models and how they combineto provide the expected behaviour of intelligent tutoring agents by representing andmanaging domain knowledge, applying techniques for monitoring the progress of humanlearning, and the appropriate selection of instructional strategies for individualised tuition.From understanding the application of these concepts, this paper proposes bi-directionalhuman and machine learning as necessary for effective game-based intelligent tutoringsystems. A conceptual architecture for game-based learning ITS implementations usingmulti-agent and machine learning technologies is then outlined, and the design of StuntRobot a system for learning Newtonian Physics concepts is presented as a case-study.Keywords: intelligent tutoring systems, game-based learning, serious games