A Simulation-Based Tutor that Reasons about Multiple Agents

Christopher Rhodes Eliot III, Beverly Park Woolf

This paper examines the problem of modeling multiple agents within an intelligent simulation-based tutor. Multiple agent and planning technology were used to enable the system to critique a human agent’s reasoning about multiple agents. This perspective arises naturally whenever a student must learn to lead and coordinate a team of people. The system dynamically selected teaching goals, instantiated plans and modeled the student and the domain as it monitored the student’s progress. The tutor provides one of the first complete integrations of a real-time simulation with knowledge-based reasoning. Other novel techniques of the system are reported, such as common-sense reasoning about plans, reasoning about protocol mechanisms, and using a real-time simulation for training.

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.