OpenAI currently holds 101 public repositories out of which 20 are related to data science and machine learning.
| Name | Description | Language | Stars | License |
|---|---|---|---|---|
| jukebox | Code for the paper "Jukebox: A Generative Model for Music" | Python | 2816 | Other |
| gym3 | Vectorized interface for reinforcement learning environments | Python | 37 | MIT License |
| Name | Description | Language | Stars | License |
|---|---|---|---|---|
| gym | A toolkit for developing and comparing reinforcement learning algorithms. | Python | 21268 | Other |
| baselines | OpenAI Baselines: high-quality implementations of reinforcement learning algorithms | Python | 10092 | MIT License |
| spinningup | An educational resource to help anyone learn deep reinforcement learning. | Python | 4878 | MIT License |
| requests-for-research | A living collection of deep learning problems | HTML | 1504 | N/A |
| evolution-strategies-starter | Code for the paper "Evolution Strategies as a Scalable Alternative to Reinforcement Learning" | Python | 1279 | MIT License |
| gpt-2-output-dataset | Dataset of GPT-2 outputs for research in detection, biases, and more | Python | 961 | MIT License |
| InfoGAN | Code for reproducing key results in the paper "InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets" | Python | 910 | N/A |
| supervised-reptile | Code for the paper "On First-Order Meta-Learning Algorithms" | JavaScript | 795 | MIT License |
| mlsh | Code for the paper "Meta-Learning Shared Hierarchies" | Python | 531 | N/A |
| deeptype | Code for the paper "DeepType: Multilingual Entity Linking by Neural Type System Evolution" | Python | 531 | Other |
| imitation | Code for the paper "Generative Adversarial Imitation Learning" | Python | 527 | MIT License |
| weightnorm | Example code for Weight Normalization, from "Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks" | Python | 342 | MIT License |
| vime | Code for the paper "Curiosity-driven Exploration in Deep Reinforcement Learning via Bayesian Neural Networks" | Python | 305 | N/A |
| coinrun | Code for the paper "Quantifying Transfer in Reinforcement Learning" | C++ | 278 | Other |
| robosumo | Code for the paper "Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments" | Python | 223 | N/A |
| EPG | Code for the paper "Evolved Policy Gradients" | Python | 198 | MIT License |
| safety-starter-agents | Basic constrained RL agents used in experiments for the "Benchmarking Safe Exploration in Deep Reinforcement Learning" paper. | Python | 81 | MIT License |
| train-procgen | Code for the paper "Leveraging Procedural Generation to Benchmark Reinforcement Learning" | Python | 52 | MIT License |