A high-performance distributed execution engine
Ray is a flexible, high-performance distributed execution framework.
Ray comes with libraries that accelerate deep learning and reinforcement learning development:
Ray RLlib is an RL execution toolkit built on the Ray distributed execution framework. See the user documentation and paper.
RLlib includes the following reference algorithms:
These algorithms can be run on any OpenAI Gym MDP, including custom ones written and registered by the user.
原文发布于微信公众号 - CreateAMind（createamind）