Technology News, Trends, And Future-Ready Signals

Emergence of grounded compositional language in multi-agent populations

Prediction and control with temporal segment models

Third-person imitation learning

Attacking machine learning with adversarial examples

Adversarial examples are inputs to machine learning models that an attacker has intentionally designed to cause the mode...

Adversarial attacks on neural network policies

Team update

The OpenAI team is now 45 people. Together, we’re pushing the frontier of AI capabilities—whether by validating novel id...

PixelCNN++: Improving the PixelCNN with discretized logistic mixture likelihood...

Faulty reward functions in the wild

Reinforcement learning algorithms can break in surprising, counterintuitive ways. In this post we’ll explore one failure...

Universe

We’re releasing Universe, a software platform for measuring and training an AI’s general intelligence across the world’s...

#Exploration: A study of count-based exploration for deep reinforcement learning

OpenAI and Microsoft

We’re working with Microsoft to start running most of our large-scale experiments on Azure.

On the quantitative analysis of decoder-based generative models