Interactive Ant Colony Optimization to Support Adaptation in Serious Games

Abstract

The success of serious games usually depends on their capabilities to engage learners and to provide them with personalized gaming and learning experiences. Therefore, it is important to equip a game, as an autonomous computer system, with a certain level of understanding about individual learning trajectories and gaming processes. AI and machine learning technologies increasingly enter the field; these technologies often fail, however, since serious games either pose highly complex problems (combining gaming and learning process) or do not provide the extensive data bases that would be required. An interesting new direction is augmenting the strength of AI technologies with human intuition and human cognition. In the present paper, we investigated performance of the MAXMIN Ant System, a combinatorial optimization algorithm, with and without human interventions to the algorithmic procedure. As a testbed, we used a clone of the Travelling Salesman problem, the Travelling Snakesman game. We found some evidence that human interventions result in superior performance than the algorithm alone. The results are discussed regarding the applicability of this pathfinding algorithm in adaptive games, exemplified by Micro Learning Space adaptation systems.