Optimizing Hearthstone agents using an evolutionary algorithm

doi:10.1016/j.knosys.2019.105032

Optimizing Hearthstone agents using an evolutionary algorithm

2020-01-01

19

OA

AI

P

Pablo García‐Sánchez *

DOI：10.1016/j.knosys.2019.105032

Original

Save

View PDF

Abstract

En 中文

Digital collectible card games are not only a growing part of the video game industry, but also an interesting research area for the field of computational intelligence. This game genre allows researchers to deal with hidden information, uncertainty and planning, among other aspects. This paper proposes the use of evolutionary algorithms (EAs) to develop agents who play a card game, Hearthstone, by optimizing a data-driven decision-making mechanism that takes into account all the elements currently in play. Agents feature self-learning by means of a competitive coevolutionary training approach, whereby no external sparring element defined by the user is required for the optimization process. One of the agents developed through the proposed approach was runner-up (best 6%) in an international Hearthstone Artificial Intelligence (AI) competition. Our proposal performed remarkably well, even when it faced state-of-the-art techniques that attempted to take into account future game states, such as Monte-Carlo Tree search. This outcome shows how evolutionary computation could represent a considerable advantage in developing AIs for collectible card games such as Hearthstone. (C) 2019 Elsevier B.V. All rights reserved.

Keywords:

Evolutionary algorithms

Hearthstone

Videogames

Evolution strategy

Artificial intelligence

Games

Card games

Collectible card games

Optimizing Hearthstone agents using an evolutionary algorithm

Abstract

AI Summary

Journal

Organization