Richard Liaw

I'm a first year PhD student working with Professor Joseph Gonzalez, Ken Goldberg, and Ion Stoica on systems for reinforcement learning and AI. I've dabbled in deep reinforcement learning and currently am working on machine learning applications on top of Ray. I work closely with Eric Liang on Ray Tune, a distributed hyperparameter optimization framework, and Ray RLlib, a composable and scalable reinforcement learning library. You can find these projects here: and


RLlib: Abstractions for Distributed Reinforcement Learning

Ray: A Distributed Framework for Emerging AI Applications

Real-Time Machine Learning: The Missing Pieces

Blog Posts

Nothing to Show Right Now

It appears whatever you were looking for is no longer here or perhaps wasn't here to begin with. You might want to try starting over from the homepage to see if you can find what you're after from there.