OpenAI News
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.
Topics: Models
OpenAI News
We’ve trained a human-like robot hand to manipulate physical objects with unprecedented dexterity.
OpenAI News
We explore methods for option discovery based on variational inference and make two algorithmic contributions. First: we highlight a tight connection between variational option discovery methods and variational autoencoders, and introduce Variational...
Topics: PolicyInfrastructure
Entities: PolicyInfrastructure
OpenAI News
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.
Topics: Models
OpenAI News
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...
Topics: Models
Entities: Models
OpenAI News
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...
Topics: Models
OpenAI News
Our team of five neural networks, OpenAI Five, has started to defeat amateur human teams at Dota 2.
Topics: Models
OpenAI News
The first run of our Retro Contest—exploring the development of algorithms that can generalize from previous experience—is now complete.
OpenAI News
Modeling agent behavior is central to understanding the emergence of complex phenomena in multiagent systems. Prior work in agent modeling has largely been task-specific and driven by hand-engineering domain-specific prior knowledge. We propose a general...
Topics: Policy
Entities: Policy
OpenAI News
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...
Topics: Infrastructure
Entities: Infrastructure
OpenAI News
In this paper, we introduce a system called GamePad that can be used to explore the application of machine learning methods to theorem proving in the Coq proof assistant. Interactive theorem provers such as Coq enable users to construct machine-checkable...
Topics: Models
Entities: Models