Evolving Evaluation Functions for Collectible Card Game AI
This work addresses optimization challenges in AI for strategy card games, offering incremental improvements for game developers and AI researchers.
The study investigated how genome representation and opponent choice affect the evolution of evaluation functions for collectible card game AI, finding that more complex tree-based representations and stronger opponents generally led to better performance, with specific gains in win rates against benchmark opponents.
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.