Incorporating Multiple Self-Adaptive Agents in Games

A self-adaptive system (SAS) is capable of modifying its behavior at run-time to address uncertainty. For games, these self-adaptations can present a more dynamic experience (e.g., changing difficulty, optimizing performance), thereby enabling run-time updates to mitigate potential issues experienced during gameplay. For example, a self-adaptation may result in emergent behaviors that keep the player engaged or optimize performance to support a multitude of device configurations. Notably, games that leverage a run-time feedback loop have previously demonstrated success in optimizing a game's frame rate. However, multi-agent systems that incorporate self-adaptation remain largely unexplored in the video games domain. This paper demonstrates a novel approach for using multiple goal models with competing metrics for expressing optimal behavior in balancing and mitigating video game uncertainties. To support this goal, we adapt an existing browser-based game to a new framework that incorporates two distinct self-adaptive agents with potentially competing objectives.