You're reading from Mastering Reinforcement Learning with Python Build next-generation, self-learning models using reinforcement learning techniques and best practices

Product type Paperback

Published in Dec 2020

Publisher Packt

ISBN-13 9781838644147

Length 544 pages

Edition 1st Edition

Languages

Python

Tools

PyTorch

Concepts

Reinforcement Learning

Author (1):

Enes Bilgin

View More author details

Table of Contents (24) Chapters

Preface

1. Section 1: Reinforcement Learning Foundations

2. Chapter 1: Introduction to Reinforcement Learning FREE CHAPTER

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

Extensions to DQN: Rainbow

The Rainbow improvements bring in significant performance boost over the vanilla DQN and they have become standard in most Q-learning implementations. In this section, we discuss what those improvements are, how they help, and what their relative importance are. At the end, we talk how DQN and these extensions collectively overcome the deadly triad.

The extensions

There are six extensions to DQN included in the Rainbow algorithm. These are: i) double Q-learning, ii) prioritized replay, iii) dueling networks, iv) multi-step learning, v) distributional RL, and iv) noisy nets. Let's start describing them with double Q-learning.

Double Q-learning

One of the well-known issues in Q-learning is that the Q-value estimates we obtain during learning is higher than the true Q-values because of the maximization operation . This phenomenon is called maximization bias, and the reason we run into it is that we do a maximization operation over noisy observations...