Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters

A pytorch implementation of Detectron. Both training from scratch and inferring directly from pretrained Detectron weights are available.

An annotated implementation of the Transformer paper.

Pytorch Implementation of DQN / DDQN / Prioritized replay/ noisy networks/ distributional values/ Rainbow/ hierarchical RL

Dilated RNNs in pytorch

Nested LSTM Cell

A PyTorch implementation of Rainbow DQN agent

Facebook AI Research Sequence-to-Sequence Toolkit

An open source framework for seq2seq models in PyTorch.

Tensorflow implementation for DilatedRNN

PyTorch implementation of NIPS 2017 paper Dynamic Routing Between Capsules

Kaggle | Web Traffic Forecasting 📈

1st place solution

Deep Q-Learning Network in pytorch (not actively maintained)

Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research

The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement …

Game Agent Framework. Helping you create AIs / Bots that learn to play any game you own!

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

A probabilistic programming library for Bayesian deep learning, generative models, based on Tensorflow

Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)

A python toolbox for GP analysis written in a functional programming style

Anomaly Detection with R

PyTorch implementation of Asynchronous Advantage Actor Critic (A3C) from "Asynchronous Methods for Deep Reinforcement Learning".

Evolution Strategies in PyTorch

Machine Learning on Sequential Data Using a Recurrent Weighted Average