research
∙
12/03/2019
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Deep learning frameworks have often focused on either usability or speed...
share
research
∙
06/28/2019
Growing Action Spaces
In complex tasks, such as those with large combinatorial action spaces, ...
research
∙
11/30/2018
Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger
We formulate the problem of defogging as state estimation and future sta...
research
∙
05/28/2018
Value Propagation Networks
We present Value Propagation (VProp), a parameter-efficient differentiab...
research
∙
08/07/2017
STARDATA: A StarCraft AI Research Dataset
We release a dataset of 65646 StarCraft replays that contains 1535 milli...
research
∙
02/22/2017
DeepCloak: Masking Deep Neural Network Models for Robustness Against Adversarial Samples
Recent studies have shown that deep neural networks (DNN) are vulnerable...
research
∙
11/01/2016
TorchCraft: a Library for Machine Learning Research on Real-Time Strategy Games
We present TorchCraft, a library that enables deep learning research on ...
research
∙
09/10/2016