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 humans are capable of, while
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, like learning to navigate
We’re releasing a charter that describes the principles we use to execute on OpenAI’s mission. This document reflects the strategy we’ve refined over the past two years, including feedback from many people internal and external to OpenAI. The timeline to AGI remains uncertain, but our charter will guide us in
We’re launching a transfer learning contest that measures a reinforcement learning algorithm’s ability to generalize from previous experience. In typical RL research, algorithms are tested in the same environment where they were trained, which favors algorithms which are good at memorization and have many hyperparameters. Instead, our contest tests an
On March 3rd, we hosted our first hackathon with 100 members of the artificial intelligence community. We had over 500 RSVPs arrive within two days of announcing the event — if you didn’t make it this time, please RSVP again in the future!
Thank you to Cirrascale for providing GPU machines
We’ve developed a simple meta-learning algorithm called Reptile which works by repeatedly sampling a task, performing stochastic gradient descent on it, and updating the initial parameters towards the final parameters learned on that task. This method performs as well as MAML, a broadly applicable meta-learning algorithm, while being simpler to
We’re providing 6-10 stipends and mentorship to individuals from underrepresented groups to study deep learning full-time for 3 months and open-source a project.
This is a remote program and is open to anyone with US work authorization located in US timezones (we’re happy to provide a desk in our
We’re releasing eight simulated robotics environments and a Baselines implementation of Hindsight Experience Replay, all developed for our research over the past year. We’ve used these environments to train models which work on physical robots. We’re also releasing a set of requests for robotics research.
Come to OpenAI’s office in San Francisco’s Mission District for talks and a hackathon on Saturday, March 3rd. (RSVPs are now closed. We have limited space and will curate the invite list — we’ll send email confirmations within the next few days.) Schedule of the day:
We’re excited to welcome the following new donors to OpenAI: Jed McCaleb, Gabe Newell, Michael Seibel, Jaan Tallinn, and Ashton Eaton and Brianne Theisen-Eaton. Reid Hoffman is significantly increasing his contribution. Pieter Abbeel (having completed his sabbatical with us), Julia Galef, and Maran Nelson are becoming advisors to OpenAI. Additionally,
