English

TorchCraft: a Library for Machine Learning Research on Real-Time Strategy Games

Machine Learning 2016-11-07 v2 Artificial Intelligence

Abstract

We present TorchCraft, a library that enables deep learning research on Real-Time Strategy (RTS) games such as StarCraft: Brood War, by making it easier to control these games from a machine learning framework, here Torch. This white paper argues for using RTS games as a benchmark for AI research, and describes the design and components of TorchCraft.

Keywords

Cite

@article{arxiv.1611.00625,
  title  = {TorchCraft: a Library for Machine Learning Research on Real-Time Strategy Games},
  author = {Gabriel Synnaeve and Nantas Nardelli and Alex Auvolat and Soumith Chintala and Timothée Lacroix and Zeming Lin and Florian Richoux and Nicolas Usunier},
  journal= {arXiv preprint arXiv:1611.00625},
  year   = {2016}
}
R2 v1 2026-06-22T16:39:47.430Z