Plan Recognition for Exploratory Learning Environments Using Interleaved Temporal Search

10 AI MAGAZINE Modern educational software is open ended and flexible, allowing students to build scientific models and examine properties of the models by running them and analyzing the results (Amershi and Conati 2006; Cocea, Gutierrez-Santos, and Magoulas 2008). Such exploratory learning environments (ELEs) are distinguished from more traditional e-learning systems in that students can build models from scratch by choosing objects from a depository, modifying the objects, and using these modified objects to construct new objects. They are also becoming increasingly prevalent in developing countries where access to teachers is limited. Such ELEs provide a rich educational experience for students and are generally used in classes too large for teachers to monitor all students and provide assistance when needed. Thus, there is a need to develop techniques that recognize and visualize students’ activities in a way that supports students in their work and contributes to