Pinned Repositories
dc-ign
The Deep Convolutional Inverse Graphics Network
deep-game-engine
Learning a game engine by example.
dynamics-aware-embeddings
Official implementation of DynE, Dynamics-aware Embeddings for RL
inverse-graphics-network
An implementation of (parts of) Tijmen Tieleman's PhD thesis in Theano. (Defunct, moving to Torch7.)
live-earth-desktop
A tool that continually downloads the latest GOES-East image of the Earth.
probabilistic-exploration
Using a VAE to reward a Q-learning agent for reaching unlikely states
reprieve
A library for evaluating representations.
understanding-visual-concepts
Unsupervised learning of visual concepts from video
willwhitney's Repositories
willwhitney/reprieve
A library for evaluating representations.
willwhitney/live-earth-desktop
A tool that continually downloads the latest GOES-East image of the Earth.
willwhitney/dynamics-aware-embeddings
Official implementation of DynE, Dynamics-aware Embeddings for RL
willwhitney/probabilistic-exploration
Using a VAE to reward a Q-learning agent for reaching unlikely states
willwhitney/mathsdl-spring20
Topics course Mathematics of Deep Learning at NYU, Spring 2020
willwhitney/kinova-raw
Wrapper for Kinova's C++ API for talking to the Jaco arm
willwhitney/algorithms-day
problems and code for teaching algorithms
willwhitney/description-length-probing
This is a repository with the code for the paper "Information-Theoretic Probing with Minimum Description Length"
willwhitney/dissertation
willwhitney/dyne-td3
TD3 modified to work with dynamics-aware embeddings
willwhitney/exploration-reimplementation
reimplementing my exploration-for-control work
willwhitney/jax-parallel
Code written for my post on parallelizing with JAX: http://willwhitney.com/parallel-training-jax.html
willwhitney/simple-news-host
Nothing but the news.
willwhitney/sunrise
SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning
willwhitney/baselines
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
willwhitney/cv
willwhitney/dm_control
The DeepMind Control Suite and Package
willwhitney/dyne-unified
A unified version of the codebase for DynE, which allows running jobs for both components.
willwhitney/gym
A toolkit for developing and comparing reinforcement learning algorithms.
willwhitney/handful-of-trials
Experiment code for "Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models"
willwhitney/learning-workshop-site
willwhitney/models
Models and examples built with TensorFlow
willwhitney/pytorch-a2c-ppo-acktr
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO) and Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR).
willwhitney/pytorch-pbb
A Pytorch implementation of PAC-Bayes with Backprop
willwhitney/pytorch_sac_lib
a version of denisyarats/pytorch_sac that I can use from other projects
willwhitney/quantile-baselines
willwhitney/sac_dists
messing with policy action distributions for SAC
willwhitney/Sectar
Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings
willwhitney/streetmerchant
:robot: Autonomous robot for all your electronic needs
willwhitney/willwhitney.github.io
My personal site.