Isabella's AI-Powered News Aggregator

How AI training scales

We’ve discovered that the gradient noise scale, a simple statistical metric, predicts the parallelizability of neural network training on a wide range of tasks. Since complex tasks tend to have noisier gradients, increasingly large batch sizes are likely to become useful in the future, removing one...

Quantifying generalization in reinforcement learning

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 already helped clarify a longstanding puzzle in reinforcement learning. CoinRun strikes a desirable balance in complexity: the environment is simpler...

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 practitioner in deep reinforcement learning. Spinning Up consists of crystal-clear examples of RL code, educational exercises, documentation, and tutorials.

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...

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

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.

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...

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 and mentorship to individuals from underrepresented groups to study deep learning full-time for 3 months and open-source a project.

OpenAI Fellows Winter 2019 & Interns Summer 2019

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

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

OpenAI Scholars 2018: Final projects

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

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.

Large-scale study of curiosity-driven learning

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.

Learning dexterity

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

Variational option discovery algorithms

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 developers becomes machine learning practitioners.

OpenAI Five Benchmark

The OpenAI Five Benchmark match is now over!

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...

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 t...

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 previous experience—is now complete.

Learning policy representations in multiagent systems

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 sup...

GamePad: A learning environment for theorem proving

OpenAI Fellows Fall 2018

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.

Gym Retro

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 tool we use to add new...

AI and compute

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 metric has grown by more...

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 who wins.

Evolved Policy Gradients

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 their training regime, l...