The World's Fastest
AI News Feed
Breaking AI news from 100+ sources — updated every 6 hours, 24/7.
Page 268 Stories
Quantifying generalization in reinforcement learning
We’re releasing CoinRun, a training environment which provides a metric for an agent’s ability to…
Spinning Up in Deep RL
We’re releasing Spinning Up in Deep RL, an educational resource designed to let anyone learn to become a…
Learning concepts with energy functions
We’ve developed an energy-based model that can quickly learn to identify and generate instances of…
Plan online, learn offline: Efficient learning and exploration via model-based control
Plan online, learn offline: Efficient learning and exploration via model-based control. OpenAI News -…
Reinforcement learning with prediction-based rewards
We’ve developed Random Network Distillation (RND), a prediction-based method for encouraging reinforcement…
Learning complex goals with iterated amplification
We’re proposing an AI safety technique called iterated amplification that lets us specify complicated…
OpenAI Scholars 2019: Applications open
We are now accepting applications for our second cohort of OpenAI Scholars, a program where we provide 6–10…
OpenAI Fellows Winter 2019 & Interns Summer 2019
OpenAI Fellows Winter 2019 & Interns Summer 2019. OpenAI News - artificial intelligence news.
FFJORD: Free-form continuous dynamics for scalable reversible generative models
FFJORD: Free-form continuous dynamics for scalable reversible generative models. OpenAI News - artificial…
OpenAI Scholars 2018: Final projects
OpenAI Scholars 2018: Final projects. OpenAI News - artificial intelligence news.
The International 2018: Results
OpenAI Five lost two games against top Dota 2 players at The International in Vancouver this week,…
Large-scale study of curiosity-driven learning
Large-scale study of curiosity-driven learning. OpenAI News - artificial intelligence news.
OpenAI Five Benchmark: Results
Yesterday, OpenAI Five won a best-of-three against a team of 99.95th percentile Dota…
Learning dexterity
We’ve trained a human-like robot hand to manipulate physical objects with unprecedented dexterity.
Variational option discovery algorithms
Variational option discovery algorithms. OpenAI News - artificial intelligence news.
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…
OpenAI Five Benchmark
OpenAI Five Benchmark. OpenAI News - artificial intelligence news.
Glow: Better reversible generative models
We introduce Glow, a reversible generative model which uses invertible 1x1 convolutions. It…
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…
OpenAI Five
Our team of five neural networks, OpenAI Five, has started to defeat amateur human teams at Dota 2.
Retro Contest: Results
The first run of our Retro Contest—exploring the development of algorithms that can generalize from…
Learning policy representations in multiagent systems
Learning policy representations in multiagent systems. OpenAI News - artificial intelligence news.
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…
GamePad: A learning environment for theorem proving
GamePad: A learning environment for theorem proving. OpenAI News - artificial intelligence news.