Search the full wire by company, model, lab, or keyword. Every story we have ever aggregated.
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 whom have played Dota professionally—in front of a live audience and 100,000 concurrent livestream viewers.
We’ve trained a human-like robot hand to manipulate physical objects with unprecedented dexterity.
OMSCS CS7642 (Reinforcement Learning) - Landing rockets (fun!) via deep Q-Learning (and its variants).
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.
We introduce Glow, a reversible generative model which uses invertible 1x1 convolutions. It extends previous work on reversible generative models and simplifies the architecture. Our model can generate realistic high resolution images, supports efficient sampling, and discovers…
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 states from the…
Our team of five neural networks, OpenAI Five, has started to defeat amateur human teams at Dota 2.
The first run of our Retro Contest—exploring the development of algorithms that can generalize from previous experience—is now complete.
Technical challenges easy compared to business and people issues. Sharing at the BDA Summit.
We’ve obtained state-of-the-art results on a suite of diverse language tasks with a scalable, task-agnostic system, which we’re also releasing. Our approach is a combination of two existing ideas: transformers and unsupervised pre-training. These results provide a convincing…
We’re now accepting applications for the next cohort of OpenAI Fellows, a program which offers a compensated 6-month apprenticeship in AI research at OpenAI.
We’re releasing the full version of Gym Retro, a platform for reinforcement learning research on games. This brings our publicly-released game count from around 70 Atari games and 30 Sega games to over 1,000 games across a variety of backing emulators. We’re also releasing the…
We’re releasing an analysis showing that since 2012, the amount of compute used in the largest AI training runs has been increasing exponentially with a 3.4-month doubling time (by comparison, Moore’s Law had a 2-year doubling period)[^footnote-correction]. Since 2012, this…
Culture >> Hierarchy, Process, Bureaucracy.
We’re proposing an AI safety technique which trains agents to debate topics with one another, using a human to judge who wins.
And my idiosyncratic journey to VP of Data Science at Lazada (Alibaba). A Lunchtime chat at INSEAD.
We’re releasing an experimental metalearning approach called Evolved Policy Gradients, a method that evolves the loss function of learning agents, which can enable fast training on novel tasks. Agents trained with EPG can succeed at basic tasks at test time that were outside…
We’re launching a transfer learning contest that measures a reinforcement learning algorithm’s ability to generalize from previous experience.
On March 3rd, we hosted our first hackathon with 100 members of the artificial intelligence community.
We’ve developed a simple meta-learning algorithm called Reptile which works by repeatedly sampling a task, performing stochastic gradient descent on it, and updating the initial parameters towards the final parameters learned on that task. Reptile is the application of the…
We’re providing 6–10 stipends and mentorship to individuals from underrepresented groups to study deep learning full-time for 3 months and open-source a project.