The Wayback Machine - https://web.archive.org/web/20180903115608/https://openai.com/systems/

Systems

OpenAI builds free software for training, benchmarking, and experimenting with AI.

Platforms

Systems for Learning

We're curating problem sets and baseline implementations for artificial agents.

Enjoy building cutting-edge systems?

View open positions

Gym

Toolkit for developing and comparing reinforcement learning algorithms.

Baselines

High-quality implementations of reinforcement learning algorithms.

Tools

Tools for Research

We build and open-source AI algorithm implementations, tools for managing research infrastructure, and software libraries for training and analyzing models.

python Roboschool Open-source software for robot simulation, integrated with OpenAI Gym.

python evolution-strategies-starter A distributed implementation of the algorithm described in Evolution Strategies as a Scalable Alternative to Reinforcement Learning.

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

python Universe Turn any application into a Gym environment.

python kubernetes-ec2-autoscaler A batch-optimized scaling manager for Kubernetes.

python pixel-cnn A Python3 / Tensorflow implementation of our PixelCNN++ generative model.

View more on GitHub