Behaviour oriented design for real-time-strategy games: An approach on iterative development for STARCRAFT AI

Design is an essential part of all games and narratives, yet designing and implementing believable game strategies can be time consuming and error-prone. This motivates the development and application of systems AI methodologies. Here we demonstrate for the first time the iterative development of agent behaviour for a real-time strategy game (here StarCraft) utilising Behaviour Oriented Design (BOD). BOD provides focus on the robust creation and easy adjustment of modular and hierarchical cognitive agents. We demonstrate BOD’s usage in creating an AI capable of playing the StarCraft character the Zerg hive mind, and document its performance against a variety of opponent AI systems. In describing our tool-driven development process, we also describe the new Abode IDE, provide a brief literature review situating BOD in the AI game literature, and propose possible future work.