Skip to main content
Join Community

Search AI Workflow Pro

Search tools, categories, stacks, and pages

Fresh daily

AI News

Latest AI tool releases, research breakthroughs, and industry news.

AllReleasesResearchFundingTutorialsOpinion

Older

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 near, above, between, closest, and furthest, expressed as sets of 2d points. Our model learns these concepts after only five demonstrations. We also show cross-domain transfer: we use concepts learned in a 2d particle environment to solve tasks on a 3-dimensional physics-based robot.

OpenAI Blog·Nov 7research

Plan online, learn offline: Efficient learning and exploration via model-based control

OpenAI Blog·Nov 5research

Reinforcement learning with prediction-based rewards

We’ve developed Random Network Distillation (RND), a prediction-based method for encouraging reinforcement learning agents to explore their environments through curiosity, which for the first time exceeds average human performance on Montezuma’s Revenge.

OpenAI Blog·Oct 31research

Learning complex goals with iterated amplification

We’re proposing an AI safety technique called iterated amplification that lets us specify complicated behaviors and goals that are beyond human scale, by demonstrating how to decompose a task into simpler sub-tasks, rather than by providing labeled data or a reward function. Although this idea is in its very early stages and we have only completed experiments on simple toy algorithmic domains, we’ve decided to present it in its preliminary state because we think it could prove to be a scalable approach to AI safety.

OpenAI Blog·Oct 22research

OpenAI Fellows Winter 2019 & Interns Summer 2019

We are now accepting applications for OpenAI Fellows and Interns for 2019.

OpenAI Blog·Oct 9research

FFJORD: Free-form continuous dynamics for scalable reversible generative models

OpenAI Blog·Oct 2research

OpenAI Scholars 2018: Final projects

Our first cohort of OpenAI Scholars has now completed the program.

OpenAI Blog·Sep 10research

The International 2018: Results

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 20–35 minutes of both games.

OpenAI Blog·Aug 23research

Large-scale study of curiosity-driven learning

OpenAI Blog·Aug 13research

OpenAI Five Benchmark: Results

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.

OpenAI Blog·Aug 6research

Learning dexterity

We’ve trained a human-like robot hand to manipulate physical objects with unprecedented dexterity.

OpenAI Blog·Jul 30research

Variational option discovery algorithms

OpenAI Blog·Jul 26research

OpenAI Five Benchmark

The OpenAI Five Benchmark match is now over!

OpenAI Blog·Jul 18research

Glow: Better reversible generative models

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 features that can be used to manipulate attributes of data. We’re releasing code for the model and an online visualization tool so people can explore and build on these results.

OpenAI Blog·Jul 9research

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, better than any previously published result. Our algorithm is simple: the agent plays a sequence of games starting from carefully chosen states from the demonstration, and learns from them by optimizing the game score using PPO, the same reinforcement learning algorithm that underpins OpenAI Five.

OpenAI Blog·Jul 4research

OpenAI Five

Our team of five neural networks, OpenAI Five, has started to defeat amateur human teams at Dota 2.

OpenAI Blog·Jun 25research

Retro Contest: Results

The first run of our Retro Contest—exploring the development of algorithms that can generalize from previous experience—is now complete.

OpenAI Blog·Jun 22research

Learning policy representations in multiagent systems

OpenAI Blog·Jun 17research

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, which we’re also releasing. Our approach is a combination of two existing ideas: transformers and unsupervised pre-training. These results provide a convincing example that pairing supervised learning methods with unsupervised pre-training works very well; this is an idea that many have explored in the past, and we hope our result motivates further research into applying this idea on larger and more diverse datasets.

OpenAI Blog·Jun 11research

GamePad: A learning environment for theorem proving

OpenAI Blog·Jun 2research