Evolutionary Machine Learning for RTS Game StarCraft

Authors

  • Lianlong Wu University of Oxford
  • Andrew Markham University of Oxford

DOI:

https://doi.org/10.1609/aaai.v31i1.11109

Keywords:

Genetic Algorithm, Machine Learning, RTS Game, Artificial Intelligence, StarCraft

Abstract

Real-Time Strategy (RTS) games involve multiple agents acting simultaneously, and result in enormous state dimensionality. In this paper, we propose an abstracted and simplified model for the famous game StarCraft, and design a dynamic programming algorithm to solve the building order problem, which takes minimal time to achieve a specific target. In addition, Genetic Algorithms (GA) are used to find an optimal target for the opening stage.

AAAI-2017 Proceedings Cover

Downloads

Published

2017-02-12

How to Cite

Wu, L., & Markham, A. (2017). Evolutionary Machine Learning for RTS Game StarCraft. Proceedings of the AAAI Conference on Artificial Intelligence, 31(1). https://doi.org/10.1609/aaai.v31i1.11109

Issue

Vol. 31 No. 1 (2017): Thirty-First AAAI Conference on Artificial Intelligence

Section

Student Abstract Track