Deep surrogate assisted MAP-elites for automated hearthstone deckbuilding

Yulun Zhang, Matthew C. Fontaine, Amy K. Hoover, Stefanos Nikolaidis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Scopus citations

Abstract

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 a 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 deck-building 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 automated Hearthstone deckbuilding. We include the source code for all the experiments at: https://github.com/icaros-usc/EvoStone2.

Original languageEnglish (US)
Title of host publicationGECCO 2022 - Proceedings of the 2022 Genetic and Evolutionary Computation Conference
PublisherAssociation for Computing Machinery, Inc
Pages158-167
Number of pages10
ISBN (Electronic)9781450392372
DOIs
StatePublished - Jul 8 2022
Event2022 Genetic and Evolutionary Computation Conference, GECCO 2022 - Virtual, Online, United States
Duration: Jul 9 2022Jul 13 2022

Publication series

NameGECCO 2022 - Proceedings of the 2022 Genetic and Evolutionary Computation Conference

Conference

Conference2022 Genetic and Evolutionary Computation Conference, GECCO 2022
Country/TerritoryUnited States
CityVirtual, Online
Period7/9/227/13/22

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Software
  • Theoretical Computer Science

Keywords

  • Deep Neural Networks
  • MAP-Elites
  • Surrogate Modeling

Fingerprint

Dive into the research topics of 'Deep surrogate assisted MAP-elites for automated hearthstone deckbuilding'. Together they form a unique fingerprint.

Cite this