Faulty Reward Functions in the Wild

Reinforcement learning algorithms can break in surprising, counterintuitive ways. In this post we'll explore one failure mode, which is where you misspecify your reward function.

December 21, 2016

Universe

We're releasing Universe, a software platform for measuring and training an AI's general intelligence across the world's supply of games, websites and other applications.

December 05, 2016

OpenAI and Microsoft

We're working with Microsoft to start running most of our large-scale experiments on Azure. This will make Azure the primary cloud platform that OpenAI is using for deep learning and AI, and will let us conduct more research and share the results with the world.

November 15, 2016

Report from the Self-Organizing Conference

Our first group learning experiment! Last week we hosted over a hundred and fifty AI practitioners in our offices for our first self-organizing conference on machine learning. The goal was to accelerate AI research by bringing a diverse group of people together and making it easy for them to educate each other and generate new ideas. To achieve this we sought to build an entire event around the chance hallway conversations, serendipitous lunches and inspiring encounters that people have at traditional conferences.

October 13, 2016

Infrastructure for Deep Learning

Deep learning is an empirical science, and the quality of a group's infrastructure is a multiplier on progress. Fortunately, today's open-source ecosystem makes it possible for anyone to build great deep learning infrastructure.

August 29, 2016

Machine Learning Unconference

The latest information about the Unconference is now available at the Unconference wiki, which will be periodically updated with more information for attendees.

August 18, 2016

Team update

We've hired more great people to help us achieve our goals. Welcome, everyone!

August 16, 2016

Special projects

Impactful scientific work requires working on the right problems — problems which are not just interesting, but whose solutions matter. In this post, we list several problem areas likely to be important both for advancing AI and for its long-run impact on society.

July 28, 2016

Concrete AI safety problems

We (along with researchers from Berkeley and Stanford) are co-authors on today's paper led by Google Brain researchers, Concrete Problems in AI Safety. The paper explores many research problems around ensuring that modern machine learning systems operate as intended. (The problems are very practical, and we've already seen some being integrated into OpenAI Gym.)

June 21, 2016

OpenAI technical goals

OpenAI’s mission is to build safe AI, and ensure AI's benefits are as widely and evenly distributed as possible. We’re trying to build AI as part of a larger community, and we want to share our plans and capabilities along the way. We’re also working to solidify our organization's governance structure and will share our thoughts on that later this year.

June 20, 2016

Generative Models

Our first research results are now live: four projects that share a common theme of enhancing or using generative models, a branch of unsupervised learning techniques in machine learning.

June 16, 2016

Team update

We'd like to welcome the latest set of team members to OpenAI (and we're still hiring!):

May 25, 2016

OpenAI Gym Beta

We're releasing the public beta of OpenAI Gym, a toolkit for developing and comparing reinforcement learning (RL) algorithms. It consists of a growing suite of environments (from simulated robots to Atari games), and a site for comparing and reproducing results.

April 27, 2016

Welcome, Pieter and Shivon!

We have two more team updates.

April 26, 2016

Team++

We've had some fantastic people join over the past few months (and we're still hiring). Welcome, everyone!

March 31, 2016

Introducing OpenAI

OpenAI is a non-profit artificial intelligence research company. Our goal is to advance digital intelligence in the way that is most likely to benefit humanity as a whole, unconstrained by a need to generate financial return.

December 11, 2015