SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 12+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.

A job launching library for docker, EC2, GCP, etc.

A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility

Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples

StarCraft II Learning Environment

µniverse: RL environments for HTML5 games

This is my implementation of the Optimality Tightening

Implementation of Policy Gradient algorithms in PyTorch. (Sequential, Distributed sync + async)

A customisable 3D platform for agent-based AI research

A starter agent that can solve a number of universe environments.

Universe: a software platform for measuring and training an AI's general intelligence across the world's supply of games, websites and other applications.

Implementation of the paper [Using Fast Weights to Attend to the Recent Past](https://arxiv.org/abs/1610.06258)

Code for the paper "Curiosity-driven Exploration in Deep Reinforcement Learning via Bayesian Neural Networks"

Code for reproducing key results in the paper "InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets"

Fast Recurrent Networks Library

M-LOOP: Machine-learning online optimization package

A toolkit for developing and comparing reinforcement learning algorithms.

rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.

PyGame Learning Environment (PLE) -- Reinforcement Learning Environment in Python.

Variational and semi-supervised neural network toppings for Lasagne

Guided Policy Search

Neural Turing Machines library in Theano with Lasagne

Code for the Neural GPU

Common interface for Theano, CGT, and TensorFlow

A curated list of deep learning resources for computer vision

Model Zoo for Deep Reinforcement Learning

2D Game Physics for Python