David Tao's repositories
lstm-contextual-decomposition
Reproducing "Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs"
aux-inputs
reinforcement learning with auxiliary inputs
generalization-rl
Code for our CMPUT 607 project, based on the paper "Protecting Against Evaluation Overfitting in Empirical Reinforcement Learning"
TextWorldACG
Scripts for generating the TextWorldACG dataset (https://arxiv.org/abs/1812.00855)
balloon-learning-environment
The Balloon Learning Environment - flying stratospheric balloons with deep reinforcement learning.
bandits
Just some stuff on bandits
COMP421-D3-Q2
stuff
cs-useful-things
Useful things that I've accumulated as an undergrad/grad student studying Computer Science.
GANs
PyTorch implementations of GAN models.
jelly-bean-world
A framework for experimenting with never-ending learning
kobuddy
Kobo database backup and parser: extracts notes, highlights, reading progress and more
mc
minecraft server for the frens
MCTS
Monte Carlo Tree Search for Q-value approximation
meta-learning
Implementations of meta-learning algorithms in TensorFlow. For use in one-shot facial recognition.
MuZero
A structured implementation of MuZero
onager
Lightweight python library for launching experiments and tuning hyperparameters, either locally or on a cluster
personal-site
My personal website - built with React, React-Router, React-Snap for Static-Export, and GitHub Pages.
Pruning-NNs
Implementing neural network pruning
qmk_firmware
Open-source keyboard firmware for Atmel AVR and Arm USB families
Rainbow
Rainbow: Combining Improvements in Deep Reinforcement Learning
rl-competition
Repository for the 2009 RL Competition codebase
RL-Coursera
Implementations of Coursera Reinforcement Learning Specialization
rlpyt
Reinforcement Learning in PyTorch
Sketch-RNN
Pytorch (again) implementation of sketch-rnn.
slack-bixi-bot
A small slack bot to check the status of a given bixi status
WorldModels
Reproducing/Extending the World Models paper (https://worldmodels.github.io/)