Reinforcement Learning with Ray RLlib

Reinforcement learning (RL) trains an agent to maximize a cumulative reward in an environment. The talk will start with why RL is important, how it works, and several applications of RL. The presentation continues with how RL requires a variety of computational patterns: data processing, simulations, model training, model serving. etc.

Finally, Dean will discuss how RLlib (http://rllib.io), implemented with Ray (http://ray.io), seamlessly and efficiently supports RL, providing an ideal platform for building Python-based, RL applications with an intuitive, flexible API. You will also learn how RLlib is one of the few frameworks that efficiently supports all these patterns at scale.

Bio

Dean Wampler (@deanwampler) is a Chicago-based expert in data engineering for scalable, streaming data systems and applications of machine learning and artificial intelligence (ML/AI). He is a Principal Software Engineer at Domino Data Lab.

Previously he worked at Anyscale, where he focused on scalable ML with Ray, and at Lightbend, where he developed distributed streaming data systems using Apache Spark, Apache Kafka, Kubernetes, and other tools.

Dean is the author of "Programming Scala", "What Is Ray? Distributed Computing Made Simple", "Fast Data Architectures for Streaming Applications", "Functional Programming for Java Developers", and the coauthor of "Programming Hive", all from O'Reilly.
He is a contributor to several open source projects, and a frequent conference speaker and co-organizer. Dean has a Ph.D. in Physics from the University of Washington.

Agenda:
(Times are Central Standard Time)
6:00pm - brief intros
6:05pm - Talk by Dean Wampler
6:45pm - Q&A
7:00pm - end

Registration for Zoom

Note: You must register with Zoom, registering in Meetup does not give you access to the Zoom meeting. Please see the Zoom link in the Meetup page or here:

https://acm-org.zoom.us/webinar/register/WN_-NAzodn7QB6AiqYTzd2Gqg