About the Ray and Reinforcement Learning Tutorial at Ray Summit 2020
Join us for Ray Summit 2020! Watch live or stream on demand.
September 29, 2020, the day before Ray Summit 2020 starts, Anyscale is offering a full-day tutorial on Ray and Reinforcement Learning.
The morning session starts with the core concepts of Ray and how it makes distributed computing relatively easy and intuitive. It finishes with an introduction to the core concepts of reinforcement learning, in preparation for the afternoon session.
The afternoon teaches RL and Ray RLlib in more depth using practical examples. First, multi-armed bandits are used to model market conditions and investment strategies. Second, a new, state-of-the-art approach to building recommender systems with RL is explored.
Each session will end with a certification quiz.
Here is the outline:
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.
Introduction to Reinforcement Learning: Learning core concepts of RL while solving a popular test environment (CartPole) 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.
Keystone lesson: RL for Recommender Systems: New approaches to recommenders, which can be adapted to similar use cases, such as personalization.