Evolving Evaluation Functions for Collectible Card Game AI

TL;DR

This paper investigates how different genome representations and opponent testing strategies affect the evolution of evaluation functions in a collectible card game AI, with findings applicable to other domains.

Contribution

It compares three genome representations and three opponent strategies for evolving game evaluation functions in a digital card game.

Findings

Complex representations outperform simple ones in evaluation accuracy.

Opponent choice significantly influences the evolution process.

Results are generalizable beyond the tested game domain.

Abstract

In this work, we presented a study regarding two important aspects of evolving feature-based game evaluation functions: the choice of genome representation and the choice of opponent used to test the model. We compared three representations. One simpler and more limited, based on a vector of weights that are used in a linear combination of predefined game features. And two more complex, based on binary and n-ary trees. On top of this test, we also investigated the influence of fitness defined as a simulation-based function that: plays against a fixed weak opponent, plays against a fixed strong opponent, and plays against the best individual from the previous population. For a testbed, we have chosen a recently popular domain of digital collectible card games. We encoded our experiments in a programming game, Legends of Code and Magic, used in Strategy Card Game AI Competition. However, as the problems stated are of general nature we are convinced that our observations are applicable in the other domains as well.