Modular Computational Critics for Games


  • Joseph Osborn University of California, Santa Cruz
  • April Grow University of California, Santa Cruz
  • Michael Mateas University of California, Santa Cruz



Computational Critics, Game Analysis, Aesthetics, Game Mechanics, Player Models


Formal game modeling tools could support the automated analysis of game rules and rapid automated play-testing, but are not widely used. Furthermore, existing game design support tools are often limited to very specific classes of game, require significant programming expertise to use or customize, or are fully-automatic tools with limited affordances for human designers. We therefore propose a framework for authoring computational game design critics and a new game definition language (Gamelan) grounded in the conventions of board game rules. We show how a set of these critics could have detected specific, attested design problems in the development of Donald X. Vaccarino's influential card game Dominion. We also illustrate an extension of this approach to other collectible card games, turn-taking games, and games in general.




How to Cite

Osborn, J., Grow, A., & Mateas, M. (2021). Modular Computational Critics for Games. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 9(1), 163-169.