willwhitney

reprieve

A library for evaluating representations.

live-earth-desktop

A tool that continually downloads the latest GOES-East image of the Earth.

dynamics-aware-embeddings

Official implementation of DynE, Dynamics-aware Embeddings for RL

probabilistic-exploration

Using a VAE to reward a Q-learning agent for reaching unlikely states

mathsdl-spring20

Topics course Mathematics of Deep Learning at NYU, Spring 2020

kinova-raw

Wrapper for Kinova's C++ API for talking to the Jaco arm

algorithms-day

problems and code for teaching algorithms

description-length-probing

This is a repository with the code for the paper "Information-Theoretic Probing with Minimum Description Length"

dissertation

dyne-td3

TD3 modified to work with dynamics-aware embeddings

exploration-reimplementation

reimplementing my exploration-for-control work

jax-parallel

Code written for my post on parallelizing with JAX: http://willwhitney.com/parallel-training-jax.html

simple-news-host

Nothing but the news.

sunrise

SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning

baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

cv

dm_control

The DeepMind Control Suite and Package

dyne-unified

A unified version of the codebase for DynE, which allows running jobs for both components.

gym

A toolkit for developing and comparing reinforcement learning algorithms.

handful-of-trials

Experiment code for "Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models"

learning-workshop-site

models

Models and examples built with TensorFlow

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).

pytorch-pbb

A Pytorch implementation of PAC-Bayes with Backprop

pytorch_sac_lib

a version of denisyarats/pytorch_sac that I can use from other projects

quantile-baselines

sac_dists

messing with policy action distributions for SAC

Sectar

Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings

streetmerchant

:robot: Autonomous robot for all your electronic needs

willwhitney.github.io

My personal site.