Tutorial on amortized optimization for learning to optimize over continuous domains

A modular embodied agent architecture and platform for building embodied agents

A library for differentiable nonlinear optimization

Codebase for project about unsupervised skill learning via variational inference and causality.

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.