101 citations · 368 across the 4 of their papers we have counts for
4 papers
Improving Neural Language Models with a Continuous Cache
Edouard Grave, Armand Joulin, Nicolas Usunier
We propose an extension to neural network language models to adapt their prediction to the recent history. Our model is a simplified version of memory augmented networks, which sto…
TorchCraft: a Library for Machine Learning Research on Real-Time Strategy Games
Gabriel Synnaeve, Nantas Nardelli, Alex Auvolat +5
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…
Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks
Nicolas Usunier, Gabriel Synnaeve, Zeming Lin +1
We consider scenarios from the real-time strategy game StarCraft as new benchmarks for reinforcement learning algorithms. We propose micromanagement tasks, which present the proble…
Open Question Answering with Weakly Supervised Embedding Models
Antoine Bordes, Jason Weston, Nicolas Usunier
Building computers able to answer questions on any subject is a long standing goal of artificial intelligence. Promising progress has recently been achieved by methods that learn t…