Ray Summit

Anyscale Academy

From Ray Beginner to Reinforcement Learning

Taking place September 29

Fee:
Attendees: $100
Students: $50

This five hour tutorial will occur in two sessions, 2.5 hours in the morning and 2.5 hours in the afternoon, will take you from being a Ray beginner to using Ray for reinforcement learning. You will receive a certificate of completion from Anyscale after completing the course and taking the two quizzes in the last 30 minutes of each session.

First Session | Ray Crash Course

September 29 | 10:00 AM – 12:30 PM, Pacific Daylight Time (PDT), UTC -7 

Ray was created to make it easier to scale diverse computation tasks and distributed state across a cluster, with a minimum of distributed systems expertise and knowledge required. You’ll learn how Ray meets these goals with a concise, intuitive API while performing efficient scheduling and execution of tasks for you. You’ll learn this API and see how it breaks through the constraints of the Python interpreter’s global interpreter lock. Whether you need better utilization of the cores in your workstation or you need massive compute scheduled across a cluster, you’ll understand how to leverage Ray to meet your computation needs.

Lessons:

  • Ray Tasks: Distributed, stateless computing
  • Ray Actors: Distributed, stateful computing
  • Ray Multiprocessing: Ray replacements for popular multiprocessing and multithreading libraries that let you break the single-node boundary.
  • Ray Parallel Iterators: Processing streams (or batch data) with Ray
  • Quiz (required for the certificate)

Second Session | Reinforcement Learning with Ray RLlib and Tune

September 29 | 2:00 PM – 4:30 PM Pacific Daylight Time (PDT), UTC -7

Using hands-on examples, we’ll learn how to use RLlib and Tune to train and run reinforcement learning systems. If you’re new to RL, we’ll cover the basic concepts as we go.

Lessons:

  • RL Crash Course with “Cart Pole”: Learning core concepts of RL while solving a popular test environment with production-ready algorithms and tools.
  • Optimizing Market Investments with Multi-Armed Bandit: A real-world problem addressed with a “constrained” class of RL algorithms.
  • RL for Recommender Systems: New approaches to recommenders, adaptable to similar problems, like personalization.
  • Quiz (required for the certificate)