Deep Surrogate Assisted MAP-Elites for Automated Hearthstone Deckbuilding
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2021
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911472285646848 |
|---|---|
| author | Zhang, Yulun Fontaine, Matthew C. Hoover, Amy K. Nikolaidis, Stefanos |
| author_facet | Zhang, Yulun Fontaine, Matthew C. Hoover, Amy K. Nikolaidis, Stefanos |
| contents | 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 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 automated Hearthstone deckbuilding. We include the source code for all the experiments at: https://github.com/icaros-usc/EvoStone2. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2112_03534 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Deep Surrogate Assisted MAP-Elites for Automated Hearthstone Deckbuilding Zhang, Yulun Fontaine, Matthew C. Hoover, Amy K. Nikolaidis, Stefanos Neural and Evolutionary Computing 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 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 automated Hearthstone deckbuilding. We include the source code for all the experiments at: https://github.com/icaros-usc/EvoStone2. |
| title | Deep Surrogate Assisted MAP-Elites for Automated Hearthstone Deckbuilding |
| topic | Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2112.03534 |