Evolutionary Tabletop Game Design: A Case Study in the Risk Game

TL;DR

This study extends Evolutionary Game Design to tabletop games by incorporating dice, cards, and maps, and applies it to a simplified two-player Risk variant. A genetic algorithm evolves both game parameters and the map topology, with a rule-based playtester to enable scalable evaluation via predefined quality metrics. The results show that the approach can generate playable Risk variants on smaller maps that are more balanced and shorter, though some runs yield nearly trivial experiences, highlighting the need for stronger agents and broader testing. The work lays groundwork for automatic design of tabletop games beyond classic board games and discusses future improvements including more powerful search strategies and human-in-the-loop validation.

Abstract

Creating and evaluating games manually is an arduous and laborious task. Procedural content generation can aid by creating game artifacts, but usually not an entire game. Evolutionary game design, which combines evolutionary algorithms with automated playtesting, has been used to create novel board games with simple equipment; however, the original approach does not include complex tabletop games with dice, cards, and maps. This work proposes an extension of the approach for tabletop games, evaluating the process by generating variants of Risk, a military strategy game where players must conquer map territories to win. We achieved this using a genetic algorithm to evolve the chosen parameters, as well as a rules-based agent to test the games and a variety of quality criteria to evaluate the new variations generated. Our results show the creation of new variations of the original game with smaller maps, resulting in shorter matches. Also, the variants produce more balanced matches, maintaining the usual drama. We also identified limitations in the process, where, in many cases, where the objective function was correctly pursued, but the generated games were nearly trivial. This work paves the way towards promising research regarding the use of evolutionary game design beyond classic board games.

Figures (6)

• Figure 1: Map visualization on the implemented Risk engine.
• Figure 2: Genetic algorithm for generating Risk game versions. Numbers indicate the subsection describing each component. Playtests generate turn and endgame metrics, being described in the same subsection. Crossover, mutation and map validity are also described in a single subsection.
• Figure 3: Fitness throughout the execution that resulted in the best fitness and the second-best fitness at the end of the process.
• Figure 4: Final fitness versus number of generations.
• Figure 5: Final fitness versus mutation rates.