A Taxonomy of Collectible Card Games from a Game-Playing AI Perspective

TL;DR

This work proposes a unified, AI-focused taxonomy of collectible card games (CCGs) by analyzing a representative set of ten active CCGs and decomposing them into dimensions relevant to game-playing AI, including cards, game modes, classes/heroes, redraw, turns, resources, zones, combat, actions, and win conditions. By examining rules, mechanics, and mode variants, the authors highlight both shared structure and domain-specific differences, and discuss their implications for AI research, such as complexity considerations and the design of more generic agents. The main contributions are the AI-centric taxonomy framework and the discussion of how varying rules and modes impact deck-building and battle planning, which can inform playtesting, AI design, and game development. The paper also outlines future directions to formalize decision problems faced by players and to extend the taxonomy to cover broader aspects of CCGs.

Abstract

Collectible card games are challenging, widely played games that have received increasing attention from the AI research community in recent years. Despite important breakthroughs, the field still poses many unresolved challenges. This work aims to help further research on the genre by proposing a taxonomy of collectible card games by analyzing their rules, mechanics, and game modes from the perspective of game-playing AI research. To achieve this, we studied a set of popular games and provided a thorough discussion about their characteristics.