Latest AI/ML News
1145 articles · OpenAI Blog
Our team of five neural networks, OpenAI Five, has started to defeat amateur human teams at Dota 2.
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 publishe…
We introduce Glow, a reversible generative model which uses invertible 1x1 convolutions. It extends previous work on reversible generative models and…
Our first class of OpenAI Scholars is underway, and you can now follow along as this group of experienced software developers becomes machine learning…
We’ve trained a human-like robot hand to manipulate physical objects with unprecedented dexterity.
Yesterday, OpenAI Five won a best-of-three against a team of 99.95th percentile Dota players: Blitz, Cap, Fogged, Merlini, and MoonMeander—four of who…
OpenAI Five lost two games against top Dota 2 players at The International in Vancouver this week, maintaining a good chance of winning for the first…
Our first cohort of OpenAI Scholars has now completed the program.
We are now accepting applications for OpenAI Fellows and Interns for 2019.
We are now accepting applications for our second cohort of OpenAI Scholars, a program where we provide 6–10 stipends and mentorship to individuals fro…
We’re proposing an AI safety technique called iterated amplification that lets us specify complicated behaviors and goals that are beyond human scale,…
We’ve developed Random Network Distillation (RND), a prediction-based method for encouraging reinforcement learning agents to explore their environmen…
We’ve developed an energy-based model that can quickly learn to identify and generate instances of concepts, such as near, above, between, closest, an…
We’re releasing Spinning Up in Deep RL, an educational resource designed to let anyone learn to become a skilled practitioner in deep reinforcement le…
We’re releasing CoinRun, a training environment which provides a metric for an agent’s ability to transfer its experience to novel situations and has…