You're reading from Mastering Reinforcement Learning with Python

Product type Book

Published in Dec 2020

Publisher Packt

ISBN-13 9781838644147

Pages 544 pages

Edition 1st Edition

Languages

Python

Concepts

Reinforcement Learning

Author (1):

Enes Bilgin

Table of Contents (24) Chapters

Preface

1. Section 1: Reinforcement Learning Foundations

2. Chapter 1: Introduction to Reinforcement Learning

3. Chapter 2: Multi-Armed Bandits

4. Chapter 3: Contextual Bandits

5. Chapter 4: Makings of a Markov Decision Process

6. Chapter 5: Solving the Reinforcement Learning Problem

7. Section 2: Deep Reinforcement Learning

8. Chapter 6: Deep Q-Learning at Scale

9. Chapter 7: Policy-Based Methods

10. Chapter 8: Model-Based Methods

11. Chapter 9: Multi-Agent Reinforcement Learning

12. Section 3: Advanced Topics in RL

13. Chapter 10: Introducing Machine Teaching

14. Chapter 11: Achieving Generalization and Overcoming Partial Observability

15. Chapter 12: Meta-Reinforcement Learning

16. Chapter 13: Exploring Advanced Topics

17. Section 4: Applications of RL

18. Chapter 14: Solving Robot Learning

19. Chapter 15: Supply Chain Management

20. Chapter 16: Personalization, Marketing, and Finance

21. Chapter 17: Smart City and Cybersecurity

22. Chapter 18: Challenges and Future Directions in Reinforcement Learning

23. Other Books You May Enjoy

Leave a review - let other readers know what you think

Chapter 2: Multi-Armed Bandits

When you log on to your favorite social media app, chances are you see one of the many versions of the app that are tested at that time. When you visit a website, the ads displayed to you are tailored to your profile. In many online shopping platforms, the prices are determined dynamically. Do you know what all these have in common? They are often modeled as multi-armed bandit (MAB) problems to identify optimal decisions. A MAB problem is a form of reinforcement learning (RL), where the agent makes decisions in a problem horizon that consists of a single step. Therefore, the goal is to maximize only the immediate reward, and there are no consequences considered for any subsequent steps. While this is a simplification over multi-step RL, the agent must still deal with a fundamental trade-off of RL: Exploration of new actions that could possibly lead to higher rewards, versus exploitation of the actions that are known to be decent. A wide range of business...