Eric Liang

Eric Liang is a PhD student working on distributed systems and applications for reinforcement learning. Before grad school, he spent 4 years working in industry in storage infrastructure at Google and on Spark at Databricks.

Publications

Benchmarks for reinforcement learning in mixed-autonomy traffic

RLlib: Abstractions for Distributed Reinforcement Learning

Ray: A Distributed Framework for Emerging AI Applications

Blog Posts

An Open Source Tool for Scaling Multi-Agent Reinforcement Learning

Eric Liang blog, Distributed Systems, Ray, Reinforcement Learning 0 Comments

We just rolled out general support for multi-agent reinforcement learning in Ray RLlib 0.6.0. This blog post is a brief tutorial on multi-agent RL and how we designed for it in RLlib. Our goal is to enable multi-agent RL across a range of use cases, from leveraging existing single-agent algorithms to training with custom algorithms at large scale.

Distributed Policy Optimizers for Scalable and Reproducible Deep RL

Eric Liang blog, Deep Learning, Distributed Systems, Open Source, Ray, Reinforcement Learning 0 Comments

In this blog post we introduce Ray RLlib, an RL execution toolkit built on the Ray distributed execution framework. RLlib implements a collection of distributed policy optimizers that make it easy to use a variety of training strategies with existing reinforcement learning algorithms written in frameworks such as PyTorch, TensorFlow, and Theano. This enables complex architectures for RL training (e.g., Ape-X, IMPALA), to be implemented once and reused many times across different RL algorithms and libraries. We discuss in more detail the design and performance of policy optimizers in the RLlib paper. What’s next for RLlib In the near term we plan to continue building out RLlib’s set of policy optimizers and algorithms. Our aim is for RLlib to serve …