Engineering Insights

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.

Node.js 6.14.2 (LTS)

Build a Realtime GraphQL Server with Subscriptions | Prisma

Learn how to build a realtime GraphQL server with subscriptions so clients can receive live event updates.

Node.js 10.0.0 (Current)

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, like learning to navigate to an object on a different side of the room from where it was placed during training.

Gotta Learn Fast: A new benchmark for generalization in RL

Retro Contest

We’re launching a transfer learning contest that measures a reinforcement learning algorithm’s ability to generalize from previous experience.

Node.js 9.11.1 (Current)