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

Gabriel Synnaeve (1) , Nantas Nardelli (2) , Alex Auvolat (3) , Soumith Chintala (1) , Timothée Lacroix (4) , Zeming Lin (1) , Florian Richoux (5, 6) , Nicolas Usunier (7)

1 FAIR - Facebook AI Research [Paris]
2 University of Oxford
3 LIENS - Laboratoire d'informatique de l'école normale supérieure
4 UPE - Université Paris-Est
5 LS2N - équipe TASC - Théorie, Algorithmes et Systèmes en Contraintes
6 LS2N - Laboratoire des Sciences du Numérique de Nantes
7 Heudiasyc - Heuristique et Diagnostic des Systèmes Complexes [Compiègne]

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 [9]. This white paper argues for using RTS games as a benchmark for AI research, and describes the design and components of TorchCraft.

Domaines: Intelligence artificielle [cs.AI]

Gabriel Synnaeve, Nantas Nardelli, Alex Auvolat, Soumith Chintala, Timothée Lacroix, et al.. TorchCraft: a Library for Machine Learning Research on Real-Time Strategy Games. 2018. ⟨hal-01436134⟩