A Simulation-Based Tutor that Reasons about Multiple Agents

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.

Authors

• Christopher Rhodes Eliot III Beverly Park Woolf

Keywords

No keywords are indexed for this paper.