David Krueger's repositories
capybaralet.github.io
website
cbl-website
CBL website
academicpages.github.io
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
mopo
Code for MOPO: Model-based Offline Policy Optimization
d4rl
A benchmark for offline reinforcement learning.
manifold_mixup
Code for reproducing Manifold Mixup results (ICML 2019)
pytorch_sac
PyTorch implementation of Soft Actor-Critic (SAC)
learning-to-reweight-examples
Code for paper "Learning to Reweight Examples for Robust Deep Learning"
examples
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
smoothing
Provable adversarial robustness at ImageNet scale
annotated-transformer
http://nlp.seas.harvard.edu/2018/04/03/attention.html
alexirpan.github.io
Repo backing personal website
gail_gym
Implementation of Generatve Adversarial Imitation Learning (GAIL) for classic environments from OpenAI Gym.
Theano
Optimizing GPU-meta-programming code generating array oriented optimizing math compiler in Python
vat
Code for reproducing the results on the MNIST dataset in the paper "Distributional Smoothing with Virtual Adversarial Training"
improved-gan
code for the paper "Improved Techniques for Training GANs"
gym
A toolkit for developing and comparing reinforcement learning algorithms.
Theano_SPENs
SPENs in Theano / Keras
dqn
This is a very basic DQN implementation, which uses OpenAI's gym environment and Keras/Theano neural networks.
tensorpack
Neural Network Toolbox on TensorFlow
universe-starter-agent
A starter agent that can solve a number of universe environments.
dk_keras
keras extensions
keras
Theano-based Deep Learning library