GVGAI as a Tool for Game Design


By: Diego Perez-Liebana (University of Essex)

Description

The General Video Game AI (GVGAI) framework and competition have attracted many practitioners, researchers and students during the last couple of years. This benchmark proposes the challenge of creating agents that are able to play any game it’s given, even if it’s not known in advance, in the absence of any domain knowledge. This is proposed in different settings, from single and two-player planning problems to learning without a forward model. Besides, the competition presents another two tests for generality, namely the automatic generation of levels and rules for any game. After briefly introducing the framework and its different tracks, this tutorial will show a new feature recently added to the framework: the possibility of setting the parameters of a game described in the Video Game Description Language (VGDL) and explore the different possibilities the game rules offer. We will describe how to make a VGDL game parameterizable, and how to define a game space for it. Finally, we will show how an evolutionary algorithm, the N-tuple Bandit EA in particular, is able to tune game parameters to make it either more balanced or more challenging. In the practical part of the tutorial, we will explore how to make a GVGAI game parameterizable and how to tweak parameters to obtain the type of game desired. We will also explore different ways to evaluate the newly designed games, using bots to validate them.