Evolving Evaluation Functions for Collectible Card Game AI

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.

MCTS Based Agents for Multistage Single-Player Card Game

“…Utilising a two-step learning strategy, a model was developed that attained a 78.5% winrate when tested on 10,000 random games at the highest difficulty level. This is significantly better than the previous studies on the use of MCTS methods [9], which achieved an average winrate of 40%, as well as 60% reported for a similar collectible card game [14].…”