RT Journal Article
T1 Optimizing Hearthstone Agents using an Evolutionary Algorithm.
A1 García Sánchez, Pablo
A1 Tonda, Alberto
A1 Fernández-Leiva, Antonio José
A1 Cotta-Porras, Carlos
K1 Algoritmos evolutivos
K1 Juegos de cartas - Modelos matemáticos
AB 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.
PB Elsevier
YR 2020
FD 2020
LK https://hdl.handle.net/10630/34911
UL https://hdl.handle.net/10630/34911
LA eng
NO P. García Sánchez, A. Tonda, A.J. Fernández Leiva, C. Cotta, Optimizing Hearthstone Agents using an Evolutionary Algorithm, Knowledge-Based Systems 188:105032, 2020
NO Política de acceso abierto tomada de: https://v2.sherpa.ac.uk/id/publication/16928
NO SPIP2017-02116, EphemeCH (TIN2014-56494-C4-f{1,3}-P), DeepBio (TIN2017-85727-C4-{1,2}-P), TEC2015-68752
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 18 feb 2026