OpenAI Five Benchmark

Time until the OpenAI Five Benchmark match: Watch the livestream | Request an in-person invite We’ve removed the most significant restrictions on OpenAI Five’s gameplay — namely, wards, Roshan, and mirror match of fixed heroes, and will soon benchmark our progress by playing 99.95th-percentile Dota…

Glow: Better Reversible Generative Models

We introduce Glow, a reversible generative model which uses invertible 1×1 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…

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…

Retro Contest: Results

The first run of our Retro Contest — exploring the development of algorithms that can generalize from previous experience — is now complete. Though many approaches were tried, top results all came from tuning or extending existing algorithms such as PPO and Rainbow. There’s a…

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…

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. We designed this program for people who want to be an AI researcher, but do not have a formal background in…

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…

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 3.5 month-doubling time (by comparison, Moore’s Law had an 18-month doubling period). 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. We believe that this or a similar approach could eventually help us train AI systems to perform far more cognitively advanced tasks than…