Ray Logo
Anyscale

MARCH 29, 2022 - 9 AM PST - FREE & VIRTUAL

Production RL Summit

The reinforcement learning event designed for practitioners

Register
hero-rl-summit
hero-rl-summit

About

Production RL Summit is a free 1-day virtual event that brings together ML engineers, data scientists, and researchers pioneering the use of reinforcement learning (RL) to solve real-world business problems.

Experts from JP Morgan, Riot Games, Dow, and Siemens will share their experience taking RL projects from idea to production. Hear about the biggest technical and business challenges they faced, how they tackled them, what they learned, and the future of RL at their organizations.

And more than listen, do! At the free RL Summit you’ll have the opportunity to:

  • Learn practical tips and best practices for bringing RL into your AI portfolio.
  • Connect and share with your peers and experts in the RL community.
  • Build your RL skills with a hands-on practical introduction to RL led by Sven Mika, lead developer on the popular open source RL library, RLlib.

Speakers

Sergey Levine

Sergey Levine

Department of Electrical Engineering and Computer Sciences, UC Berkeley
Sumitra Ganesh

Sumitra Ganesh

J.P. Morgan AI Research
Ben Kasper

Ben Kasper

Riot Games
Volkmar Sterzing

Volkmar Sterzing

Siemens Technology
Marc Webber

Dr. Marc Weber

Siemens Technology
Sven Mika

Sven Mika

Anyscale
Adam Kelloway

Adam Kelloway

Dow, Inc.

Agenda

9:00 AM - 9:30 AM

[Opening Keynote] Offline reinforcement learning

Sergey Levine

Department of Electrical Engineering and Computer Sciences, UC Berkeley
9:30 AM - 10:00 AM

Reinforcement learning-based simulation of markets

Sumitra Ganesh

J.P. Morgan AI Research
10:00 AM - 10:15 AM

Break

10:15 AM - 10:45 AM

Deep reinforcement learning at Riot Games

Ben Kasper

Riot Games
10:45 AM - 11:15 AM

AlphaDow: Leveraging Ray’s ecosystem to train and deploy an RL industrial production scheduling agent

Adam Kelloway

Dow, Inc.
11:15 AM - 11:45 AM

RL in the physical world

Volkmar Sterzing
, Siemens Technology
Dr. Marc Weber
, Siemens Technology
11:45 AM - 12:45 PM

Networking

1:00 PM - 3:00 PM

[Tutorial] Reinforcement learning for recommender systems - from Contextual Bandits to SlateQ and Offline RL with Ray RLlib

Sven Mika
, Anyscale
Christy Bergman
, Anyscale
Richard Liaw
, Anyscale
Avnish Narayan
, Anyscale

Who should attend?

  • ML engineers, researchers, and data scientists interested in bringing RL into their AI strategy
  • RL practitioners who want to connect with and learn from their industry experts and peers
  • Students and academics interested in learning about applied RL use cases

Contact

Questions?
Please email us at events@anyscale.com