Hands-on RL with Ray’s RLlib

Overview

“Hands-on RL with Ray’s RLlib” is a beginners tutorial for working with reinforcement learning (RL) environments, models, and algorithms using Ray’s RLlib library. It offers high scalability, a large list of algos to choose from (offline, model-based, model-free, etc..), support for TensorFlow and PyTorch, and a unified API for a variety of applications. This tutorial includes a brief introduction to provide an overview of concepts (e.g. why RL) before proceeding to RLlib models, hyperparameter tuning, debugging, student exercises, Q/A, and more. All code will be provided as .py files in a GitHub repo.

Intended Audience

• Python programmers who want to get started with reinforcement learning and RLlib

Prerequisites

• Some Python programming experience
• Some familiarity with machine learning
• Experience in reinforcement learning and Ray would be helpful, but isn’t required
• Experience with TensorFlow or PyTorch would be helpful, but isn’t required

Key Takeaways

• What is reinforcement learning and why RLlib
• How to configure and hyperparameter tune RLlib
• RLlib debugging best practices

Tutorial Outline

Other Recommended Readings

• Attention Nets and More with RLlib's Trajectory View API
• Intro to RLlib: Example Environments
• Reinforcement Learning with RLlib in the Unity Game Engine