A multi-agent system for learner assessment in serious games: Application to learning processes in crisis management

Abstract

Serious Games (SG) are more and more used for training in various domains, especially in crisis management domain. In order to improve training results, learner assessment can provide insights on what went right or wrong during a training session. Learner assessment requires monitoring (data acquisition in a virtual environment) and supporting learners' feedback (on learners' decisions and actions), which Intelligent Tutoring Systems address as a main issue, as a mean to individualise learning. In this paper, to enhance learning and pedagogy in virtual environment of collaborative serious games for crisis management, we propose a distributed and multicriteria evaluation approach supported both at modelling and software level by a multi-agent system (MAS). In the context of collaborative serious games for crisis management, this supported assessment has to consider individual and collective assessment. The multi-agent based assessment method proposed is integrated in a serious game developed in the SIMFOR project dedicated to crisis management. An illustrative example is presented to describe the evaluation process.