Scenario control for (serious) games using self-organizing multi-agent systems

In order to achieve an optimal learning in a serious game, a continuously adapted game experience is needed. This paper presents a multi-agent system which dynamically control the orientation of a game according to players´ actions. Irrespective of the application domain, a game scenario is abstracted and elements composing it are identified. These elements are then encapsulated into cooperative agents which interact in order to collectively adapt the scenario they are related to. The feasibility of this approach is shown by applying it to a real game scenario.