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

Thompson (Posterior) sampling

The goal in MAB problems is to estimate the parameter(s) of the reward distribution for each arm (that is ad to display in the above example). In addition, measuring our uncertainty about our estimate is a good way to guide the exploration strategy. This problem very much fits into the Bayesian inference framework, which is what Thompson sampling leverages. Bayesian inference starts with a prior probability distribution, an initial idea, for the parameter , and updates this prior as data becomes available. Here, refers to the mean and variance for a normal distribution, and to the probability of observing a "1" for Bernoulli distribution. So, the Bayesian approach treats the parameter as a random variable given the data.

The formula for this is given by:

In this formula, is the prior distribution of , which represents the current hypothesis on its distribution. represents the data, with which we obtain a posterior...