Monte Carlo tree search experiments in hearthstone
Authors:
- 1 August 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 272-279
Abstract
In this paper, we introduce a Monte-Carlo tree search (MCTS) approach for the game "Hearthstone: Heroes of Warcraft". We argue that, in light of the challenges posed by the game (such as uncertainty and hidden information), Monte Carlo tree search offers an appealing alternative to existing AI players. Additionally, by enriching MCTS with a properly constructed heuristic, it is possible to introduce significant gains in performance. We illustrate through extensive empirical validation the superior performance of our approach against vanilla MCTS and the current state-of-the art AI for Hearthstone.Keywords
This publication has 12 references indexed in Scilit:
- I am a legend: Hacking hearthstone using statistical learning methods2016
- Mastering the game of Go with deep neural networks and tree searchNature, 2016
- Latent Predictor Networks for Code Generation2016
- Control-Alt-Hack2013
- Ensemble Determinization in Monte Carlo Tree Search for the Imperfect Information Card Game Magic: The GatheringIEEE Transactions on Computational Intelligence and AI in Games, 2012
- Current Frontiers in Computer GoIEEE Transactions on Computational Intelligence and AI in Games, 2010
- Monte Carlo search applied to card selection in Magic: The Gathering2009
- PROGRESSIVE STRATEGIES FOR MONTE-CARLO TREE SEARCHNew Mathematics and Natural Computation, 2008
- Finite-time Analysis of the Multiarmed Bandit ProblemMachine Learning, 2002
- A Comparison of Selection Schemes Used in Evolutionary AlgorithmsEvolutionary Computation, 1996