Engineering Insights

Evolution strategies as a scalable alternative to reinforcement learning

We’ve discovered that evolution strategies (ES), an optimization technique that’s been known for decades, rivals the performance of standard reinforcement learning (RL) techniques on modern RL benchmarks (e.g. Atari/MuJoCo), while overcoming many of RL’s inconveniences.

Node.js 7.7.4 (Current)

Node.js 6.10.1 (LTS)

Node.js 4.8.1 (LTS)

One-shot imitation learning

Distill

We’re excited to support today’s launch of Distill, a new kind of journal aimed at excellent communication of machine learning results (novel or existing).

Building a Real-Time Chat with GraphQL Subscriptions and Apollo

Build a real-time chat app with GraphQL subscriptions, Apollo, and live location updates on a shared map.

Learning to communicate

In this post we’ll outline new OpenAI research in which agents develop their own language.