MSIP: Agents embodying a category-based learning process for the ITS tutor to self-improve its instructional plans

• Main Authors: Legaspi, Roberto S., Sison, Raymund, Numao, Masayuki
• Format: text
• Published: Animo Repository 2004
• Subjects: Intelligent tutoring systems; Multiagent systems; Computer Sciences
• Online Access: https://animorepository.dlsu.edu.ph/faculty_research/3839; https://animorepository.dlsu.edu.ph/context/faculty_research/article/4841/type/native/viewcontent/978_3_540_28633_2_14.html
• Institution: De La Salle University

We have conceived of a Multi-agent Self-improving Planner (MSIP) within the tutor module of an intelligent tutoring system (ITS). It embodies a learning process that utilizes knowledge about different student categories to adapt and improve its instructional plans on the level of these categories. In this sense, the categories become recipients and effectors of effective plans. The fundamental reason for introducing agents as learning elements is their intrinsic capability to learn and perform autonomously during on-line interaction. This paper discusses each agent's learning task and the representation of the knowledge each acquires. Empirical results drawn from performing the agents' tasks using recorded teaching scenarios validate the MSIP's learning process. © Springer-Verlag Berlin Heidelberg 2004.