I thought that it would be nice to have short and concise summaries of recent projects handy, to share them with a more general audience, including…
We’ve trained a human-like robot hand to manipulate physical objects with unprecedented dexterity.
A powerful, under-explored tool for neural network visualizations and art.
Our first class of OpenAI Scholars is underway, and you can now follow along as this group of experienced software developers becomes machine learning practitioners.
A simple and surprisingly effective family of conditioning mechanisms.
We introduce Glow, a reversible generative model which uses invertible 1×1 convolutions. It extends previous work on reversible generative models and simplifies the architecture. Our model can generate realistic high resolution images, supports efficie…
We’ve trained an agent to achieve a high score of 74,500 on Montezuma’s Revenge from a single human demonstration, better than any previously published result. Our algorithm is simple: the agent plays a sequence of games starting from carefully chosen …
Our team of five neural networks, OpenAI Five, has started to defeat amateur human teams at Dota 2.