English

StarCraft II Build Order Optimization using Deep Reinforcement Learning and Monte-Carlo Tree Search

Machine Learning 2020-06-19 v1 Artificial Intelligence

Abstract

The real-time strategy game of StarCraft II has been posed as a challenge for reinforcement learning by Google's DeepMind. This study examines the use of an agent based on the Monte-Carlo Tree Search algorithm for optimizing the build order in StarCraft II, and discusses how its performance can be improved even further by combining it with a deep reinforcement learning neural network. The experimental results accomplished using Monte-Carlo Tree Search achieves a score similar to a novice human player by only using very limited time and computational resources, which paves the way to achieving scores comparable to those of a human expert by combining it with the use of deep reinforcement learning.

Keywords

Cite

@article{arxiv.2006.10525,
  title  = {StarCraft II Build Order Optimization using Deep Reinforcement Learning and Monte-Carlo Tree Search},
  author = {Islam Elnabarawy and Kristijana Arroyo and Donald C. Wunsch},
  journal= {arXiv preprint arXiv:2006.10525},
  year   = {2020}
}
R2 v1 2026-06-23T16:26:03.628Z