Abstract | ||
---|---|---|
We present TorchCraft, a library that enables deep learning research on Real-TimeStrategy (RTS) games such as StarCraft: Brood War, by making it easier to control thesegames from a machine learning framework, here Torch [9]. This white paper argues forusing RTS games as a benchmark for AI research, and describes the design and componentsof TorchCraft. |
Year | Venue | Field |
---|---|---|
2016 | arXiv: Learning | White paper,Real-time strategy,Turns, rounds and time-keeping systems in games,Computer science,Artificial intelligence,Deep learning,Machine learning |
DocType | Volume | Citations |
Journal | abs/1611.00625 | 0 |
PageRank | References | Authors |
0.34 | 0 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Gabriel Synnaeve | 1 | 27 | 7.73 |
Nantas Nardelli | 2 | 2 | 1.05 |
alex auvolat | 3 | 24 | 3.71 |
Soumith Chintala | 4 | 2056 | 102.09 |
Timothée Lacroix | 5 | 0 | 0.68 |
Zeming Lin | 6 | 63 | 6.04 |
Florian Richoux | 7 | 81 | 6.99 |
Nicolas Usunier | 8 | 1974 | 97.52 |