Deep Surrogate Assisted MAP-Elites for Automated Hearthstone Deckbuilding


We study the problem of efficiently generating high-quality and diverse content in games. Previous work on automated deckbuilding in Hearthstone shows that the quality diversity algorithm MAP-Elites can generate a collection of high-performing decks with diverse strategic gameplay. However, MAP-Elites requires a large number of expensive evaluations to discover the diverse collection of decks. We propose assisting MAP-Elites with a deep surrogate model trained online to predict game outcomes with respect to candidate decks. MAP-Elites discovers a diverse dataset to improve the surrogate model accuracy, while the surrogate model helps guide MAP-Elites towards promising new content. In a Hearthstone deckbuilding case study, we show that our approach improves the sample efficiency of MAP-Elites and outperforms a model trained offline with random decks, as well as a linear surrogate model baseline, setting a new state-of-the-art for quality diversity approaches in the application domain of automated Hearthstone deckbuilding.

In GECCO ’22, July 9–13, 2022, Boston, MA, USA
Yulun Zhang
Yulun Zhang
Ph.D. Student

My research interests include Quality Diversity Optimization, Evolutionary Computation, Human-Robot Interaction, Multi-Robot Coordination, and Reinforcement Learning.