Interactive Learning of Expert Criteria for Rescue Simulations
Résumé
The goal of our work is to build a DSS (Decision Support System) to support resource allocation and planning for natural disaster emergencies in ur- ban areas such as Hanoi in Vietnam. The first step has been to conceive a multi- agent environment that supports simulation of disasters, taking into account geospatial, temporal and rescue organizational information. The problem we address is the acquisition of situated expert knowledge that is used to organize rescue missions. We propose an approach based on participatory techniques, in- teractive learning and machine learning. This paper presents an algorithm that incrementally builds a model of the expert knowledge by online analysis of its interaction with the simulator's proposed scenario.