Beyond Playing to Win: Creating a Team of Agents with Distinct Behaviours for Automated Gameplay

We present an approach to generate a team of General Video Game Playing (GVGP) agents with differentiated behaviours that can ultimately assist in the game development process. We consider the agent behaviour as the corresponding outcomes of playing the game: rate of wins, score, exploration, enemies killed, items collected, etc. We create and identify agents that are expected to achieve particular goals but do not necessarily simulate human behaviour during gameplay. We present a solution that, by heuristic diversification , provides a controller with different heuristics and a corresponding set of weights ; driving its actions. Given the simplicity of this behaviour-encoding and its easiness to evolve, we use MAP-Elites to generate different solutions that elicit particular behaviours and assemble a team . The resulting agents are allocated in a feature space, used to identify the expectations of each of them. We generate a team for 4 games of the General Video Game AI (GVGAI) Framework and find 6 different behaviour-type agents in each. We include an experiment to check the portability of these agents when playing alternative levels and an exploratory work aiming to use them to detect design flaws in game levels.