Research

We’re developing generally capable agents with more human-like understanding and intelligence. We care about practical engineering of deep neural networks informed by theoretical understanding. Read more about our approach.

Research Highlights


Avalon: A Benchmark for RL Generalization Using Procedurally Generated Worlds

ResearchOctober 20, 2022

What Is Avalon? Avalon is a benchmark for generalization in RL Agents in Avalon must accomplish a wide range of tasks, all with the same…

Read more

Our Research Interests


We're interested in creating intelligent and safe software agents

This goal spans a wide range of topics, including:

Deep learning theoryReinforcement learningOptimizationGeneralizationRobustness and safetyLarge scale modelsTransformersLanguage acquisitionContinual learningWorld modelsSelf supervised learning...and more

Whenever possible, we strive to collaborate with the broader research community and open source our work. However, for practical and safety reasons, we do not distribute all research results publicly. A selection of some related projects that we have published are shown below.