Introducing Activation Atlases
We’ve created activation atlases (in collaboration with Google researchers), a new technique for visualizing what…
Read at source →Source
OpenAI Blog
Updates from OpenAI
Technology · 1167 articles · page 30 of 33 · fetched less than a minute ago
Neural MMO: A massively multiagent game environment
We’re releasing a Neural MMO, a massively multiagent game environment for reinforcement learning agents. Our platform…
Read at source →
Spinning Up in Deep RL: Workshop review
On February 2, we held our first Spinning Up Workshop as part of our new education initiative at OpenAI.
Read at source →
AdSponsoredSiguimi
Pure chronological social — no algorithm
See who you follow, newest first. Free to join. Posts that stay visible — not buried by an algo.
Join siguimi.com →
AI safety needs social scientists
We’ve written a paper arguing that long-term AI safety research needs social scientists to ensure AI alignment…
Read at source →
Better language models and their implications
We’ve trained a large-scale unsupervised language model which generates coherent paragraphs of text, achieves…
Read at source →
OpenAI Fellows Summer 2018: Final projects
Our first cohort of OpenAI Fellows has concluded, with each Fellow going from a machine learning beginner to core…
Read at source →
How AI training scales
We’ve discovered that the gradient noise scale, a simple statistical metric, predicts the parallelizability of neural…
Read at source →
Quantifying generalization in reinforcement learning
We’re releasing CoinRun, a training environment which provides a metric for an agent’s ability to transfer its…
Read at source →
Spinning Up in Deep RL
We’re releasing Spinning Up in Deep RL, an educational resource designed to let anyone learn to become a skilled…
Read at source →
Learning concepts with energy functions
We’ve developed an energy-based model that can quickly learn to identify and generate instances of concepts, such as…
Read at source →
Reinforcement learning with prediction-based rewards
We’ve developed Random Network Distillation (RND), a prediction-based method for encouraging reinforcement learning…
Read at source →
Learning complex goals with iterated amplification
We’re proposing an AI safety technique called iterated amplification that lets us specify complicated behaviors and…
Read at source →
OpenAI Scholars 2019: Applications open
We are now accepting applications for our second cohort of OpenAI Scholars, a program where we provide 6–10 stipends…
Read at source →
OpenAI Fellows Winter 2019 & Interns Summer 2019
We are now accepting applications for OpenAI Fellows and Interns for 2019.
Read at source →
OpenAI Scholars 2018: Final projects
Our first cohort of OpenAI Scholars has now completed the program.
Read at source →
The International 2018: Results
OpenAI Five lost two games against top Dota 2 players at The International in Vancouver this week, maintaining a good…
Read at source →
OpenAI Five Benchmark: Results
Yesterday, OpenAI Five won a best-of-three against a team of 99.95th percentile Dota players: Blitz, Cap, Fogged,…
Read at source →
Learning dexterity
We’ve trained a human-like robot hand to manipulate physical objects with unprecedented dexterity.
Read at source →
OpenAI Scholars 2018: Meet our Scholars
Our first class of OpenAI Scholars is underway, and you can now follow along as this group of experienced software…
Read at source →
Glow: Better reversible generative models
We introduce Glow, a reversible generative model which uses invertible 1x1 convolutions. It extends previous work on…
Read at source →
Learning Montezuma’s Revenge from a single demonstration
We’ve trained an agent to achieve a high score of 74,500 on Montezuma’s Revenge from a single human demonstration,…
Read at source →
OpenAI Five
Our team of five neural networks, OpenAI Five, has started to defeat amateur human teams at Dota 2.
Read at source →
Retro Contest: Results
The first run of our Retro Contest—exploring the development of algorithms that can generalize from previous…
Read at source →
Improving language understanding with unsupervised learning
We’ve obtained state-of-the-art results on a suite of diverse language tasks with a scalable, task-agnostic system,…
Read at source →
OpenAI Fellows Fall 2018
We’re now accepting applications for the next cohort of OpenAI Fellows, a program which offers a compensated 6-month…
Read at source →
Gym Retro
We’re releasing the full version of Gym Retro, a platform for reinforcement learning research on games. This brings our…
Read at source →
AI and compute
We’re releasing an analysis showing that since 2012, the amount of compute used in the largest AI training runs has…
Read at source →
AI safety via debate
We’re proposing an AI safety technique which trains agents to debate topics with one another, using a human to judge…
Read at source →