Designing Card Game Strategies with Genetic Programming and Monte-Carlo Tree Search: A Case Study of Hearthstone

Hao Cheng Chia, Tsung Su Yeh, Tsung Che Chiang

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

Abstract

This paper addresses an agent design problem of a digital collectible card game, Hearthstone, which is a two-player turn-based game. The agent has to play cards based on the game state, the hand cards, and the deck of cards to defeat the opponent. First, we design a rule-based agent by searching for the board evaluation criterion through genetic programming (GP). Then, we integrate the rule-based agent into the Monte-Carlo tree search (MCTS) framework to generate an advanced agent. Performance of the proposed agents are verified by playing against three participants in two recent Hearthstone competitions. Experimental results showed that the GP-agent can beat a simple MCTS agent and the mid-level agent in the competition. The MCTS-GP agent showed competitive performance against the best agents in the competition. We also examine the rule found by GP and observed that GP is able to identify key attributes of game states and to combine them into a useful rule automatically.

Original languageEnglish
Title of host publication2020 IEEE Symposium Series on Computational Intelligence, SSCI 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2351-2358
Number of pages8
ISBN (Electronic)9781728125473
DOIs
Publication statusPublished - 2020 Dec 1
Event2020 IEEE Symposium Series on Computational Intelligence, SSCI 2020 - Virtual, Canberra, Australia
Duration: 2020 Dec 12020 Dec 4

Publication series

Name2020 IEEE Symposium Series on Computational Intelligence, SSCI 2020

Conference

Conference2020 IEEE Symposium Series on Computational Intelligence, SSCI 2020
CountryAustralia
CityVirtual, Canberra
Period2020/12/012020/12/04

Keywords

  • Hearthstone: Heroes of Warcraft
  • Monte-Carlo tree search
  • collectible card games
  • genetic programming

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Decision Sciences (miscellaneous)

Fingerprint Dive into the research topics of 'Designing Card Game Strategies with Genetic Programming and Monte-Carlo Tree Search: A Case Study of Hearthstone'. Together they form a unique fingerprint.

Cite this