Presented By O’Reilly and Intel AI
Put AI to work
8-9 Oct 2018: Training
9-11 Oct 2018: Tutorials & Conference
London, UK

Building reinforcement learning applications with Ray

Richard Liaw (UC Berkeley RISELab), Eric Liang (University of California, Berkeley, RISELab)
13:30–17:00 Tuesday, 9 October 2018
Location: Blenheim Room - Palace Suite
Secondary topics:  Reinforcement Learning, Text, Language, and Speech

Who is this presentation for?

  • Machine learning researchers and practitioners and data scientists who want to learn reinforcement learning and build applications

Prerequisite knowledge

  • Familiarity with Python programming, basic machine learning concepts, and reinforcement learning

Materials or downloads needed in advance

  • A laptop
  • To fully participate in the tutorial, you must have a Google account for accessing CoLab or install the dependencies for the tutorial on your laptop with pip install ray[rllib] jupyterlab tensorflow.

What you'll learn

  • Learn how to develop simple RL applications at scale with Ray and manage Ray on clusters


Reinforcement learning (RL) is emerging as a promising approach to intelligently interact with continuously changing physical or virtual environments. Advances in RL research have already shown remarkable results, such as Google’s AlphaGo beating the Go world champion, and are finding their way into self-driving cars, unmanned aerial vehicles, and surgical robotics. Not surprisingly, many see RL growing rapidly into a potentially dominant area in ML over the next decade. However, the applications of RL pose a new set of requirements, the combination of which creates a challenge for existing distributed execution frameworks: computation with millisecond latency at high throughput, adaptive construction of arbitrary task graphs, and execution of heterogeneous kernels over diverse sets of resources.

Ion Stoica, Robert Nishihara, Richard Liaw, Eric Liang, and Philipp Moritz lead a deep dive into Ray, a new distributed execution framework for reinforcement learning applications developed by machine learning and systems researchers at UC Berkeley’s RISELab, walking you through Ray’s API and system architecture and sharing application examples, including several state-of-the art RL algorithms.

Photo of Richard Liaw

Richard Liaw

UC Berkeley RISELab

Richard Liaw is a PhD student in the Berkeley Artificial Intelligence Research (BAIR) Lab and RISELab at UC Berkeley working with Joseph Gonzalez, Ion Stoica, and Ken Goldberg. He’s worked on a variety of different areas, ranging from robotics to reinforcement learning to distributed systems. He’s working on Ray, a distributed execution engine for AI applications; RLlib, a scalable reinforcement learning library; and Tune, a distributed framework for model training.

Photo of Eric Liang

Eric Liang

University of California, Berkeley, RISELab

Eric Liang is a second-year PhD student working in the University of California, Berkeley, RISELab with Ion Stoica. He works on frameworks and applications for machine learning and reinforcement learning. Previously, he spent several years working on systems in industry at Databricks and Google.