Causal Model Progressions as a Foundation for Intelligent Learning Environments

This paper describes the theoretical underpinnings and architecture of a new type of learning environment that incorporates features of microworlds and of intelligent tutoring systems. The environment is based on a progression of increasingly sophisticated, casual models that simulate domain phenomena, generate explanations, and serve as student models. Constraints on model evolution, in terms of casual consistency and learnability, are discussed and a taxonomy of models, useful for instruction, is outlined. The design principles underlying the creation of one type of casual model are then given (for zero-order models of electrical circuit behavior); and possible progressions with respect to model elaboration, order, and perspective are described in the context of presenting a theory of model evolution. Finally, the simple architecture that enables the powerful pedagogical tools of the intelligent learning environment is described, with an emphasis on the range of instructional interactions and learning strategies that are supportable. Keywords: Artificial intelligence; Education; Intelligent Tutoring Systems; Cognitive Modelling; Qualitative Models.