AI solutions for drafting in Magic: the Gathering

TL;DR

This paper introduces a large dataset of Magic: the Gathering drafts, proposes four AI drafting strategies, and benchmarks their performance, highlighting the deep neural network's superior ability to emulate human drafting behavior.

Contribution

It provides the first extensive public dataset of Magic draft data and evaluates diverse AI strategies, including a deep neural network, for drafting in this complex game.

Findings

Deep neural network outperforms other agents in emulating human drafts.

Naive Bayes and expert-tuned agents outperform simple heuristics.

AI agents show varying strengths and weaknesses throughout the draft timeline.

Abstract

Drafting in Magic the Gathering is a sub-game within a larger trading card game, where several players progressively build decks by picking cards from a common pool. Drafting poses an interesting problem for game and AI research due to its large search space, mechanical complexity, multiplayer nature, and hidden information. Despite this, drafting remains understudied, in part due to a lack of high-quality, public datasets. To rectify this problem, we present a dataset of over 100,000 simulated, anonymized human drafts collected from Draftsim.com. We also propose four diverse strategies for drafting agents, including a primitive heuristic agent, an expert-tuned complex heuristic agent, a Naive Bayes agent, and a deep neural network agent. We benchmark their ability to emulate human drafting, and show that the deep neural network agent outperforms other agents, while the Naive Bayes and expert-tuned agents outperform simple heuristics. We analyze the accuracy of AI agents across the timeline of a draft, and describe unique strengths and weaknesses for each approach. This work helps to identify next steps in the creation of humanlike drafting agents, and can serve as a benchmark for the next generation of drafting bots.