Building reinforcement learning models and AI applications with Ray
Who is this presentation for?
- Machine learning researchers and practitioners and data scientists
Building end-to-end AI applications is challenging, and building the next generation of AI applications, such as online learning and reinforcement learning (RL) is even more challenging. That is because these applications exhibit a large variety of computational patterns (e.g., data processing, simulations, model training, model serving), and none of the existing frameworks can efficiently support all these patterns at scale.
In this tutorial, we will illustrate how Ray can seamlessly and efficiently support these computational patterns, and hence provides an ideal platform for building AI applications. This tutorial will be hands on, and participants will take a deep dive into Ray, learn its API, and implement several state-of-the-art AI applications including an end-to-end application which involves training an RL model and serving predictions from it.
- Familiarity with Python programming, basic machine learning concepts, and reinforcement learning
Materials or downloads needed in advance
- A laptop
What you'll learn
- Learn how to develop simple RL applications at scale with Ray and manage Ray on clusters
Robert Nishihara is a fourth-year PhD student working in the UC Berkeley RISELab with Michael Jordan. He works on machine learning, optimization, and artificial intelligence.
Philipp Moritz is a PhD candidate in EECS at UC Berkeley, with broad interests in artificial intelligence, machine learning, and distributed systems. He is a member of the Statistical AI Lab and the RISELab.
Ion Stoica is a professor in the electrical engineering and computer sciences (EECS) department at the University of California, Berkeley, where he does research on cloud computing and networked computer systems. Previously, he worked on dynamic packet state, chord DHT, internet indirection infrastructure (i3), declarative networks, and large-scale systems, including Apache Spark, Apache Mesos, and Alluxio. He’s the cofounder of Databricks—a startup to commercialize Apache Spark—and Conviva—a startup to commercialize technologies for large-scale video distribution. Ion is an ACM fellow and has received numerous awards, including inclusion in the SIGOPS Hall of Fame (2015), the SIGCOMM Test of Time Award (2011), and the ACM doctoral dissertation award (2001).
Leave a Comment or Question
Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?
Join the conversation here (requires login)
Diversity and Inclusion Sponsor
For conference registration information and customer service
For more information on community discounts and trade opportunities with O’Reilly conferences
For information on exhibiting or sponsoring a conference
View a complete list of O'Reilly AI contacts