You're reading from Deep Reinforcement Learning with Python Master classic RL, deep RL, distributional RL, inverse RL, and more with OpenAI Gym and TensorFlow

Product type Paperback

Published in Sep 2020

Publisher Packt

ISBN-13 9781839210686

Length 760 pages

Edition 2nd Edition

Languages

Python

Tools

Deep Reinforcement Learning

Concepts

Deep Reinforcement Learning

Author (1):

Sudharsan Ravichandiran

View More author details

Table of Contents (22) Chapters

Preface

1. Fundamentals of Reinforcement Learning

2. A Guide to the Gym Toolkit FREE CHAPTER

3. The Bellman Equation and Dynamic Programming

4. Monte Carlo Methods

5. Understanding Temporal Difference Learning

6. Case Study – The MAB Problem

7. Deep Learning Foundations

8. A Primer on TensorFlow

9. Deep Q Network and Its Variants

10. Policy Gradient Method

11. Actor-Critic Methods – A2C and A3C

12. Learning DDPG, TD3, and SAC

13. TRPO, PPO, and ACKTR Methods

14. Distributional Reinforcement Learning

15. Imitation Learning and Inverse RL

16. Deep Reinforcement Learning with Stable Baselines

17. Reinforcement Learning Frontiers

18. Other Books You May Enjoy

19. Index

Appendix 1 – Reinforcement Learning Algorithms

1. Appendix 2 – Assessments

Comparing the DP, MC, and TD methods

So far, we have learned several interesting and important reinforcement learning algorithms, such as DP (value iteration and policy iteration), MC methods, and TD learning methods, to find the optimal policy. These are called the key algorithms in classic reinforcement learning, and understanding the differences between these three algorithms is very important. So, in this section, we will recap the differences between the DP, MC, and TD learning methods.

Dynamic programming (DP), that is, the value and policy iteration methods, is a model-based method, meaning that we compute the optimal policy using the model dynamics of the environment. We cannot apply the DP method when we don't have the model dynamics of the environment.

We also learned about the Monte Carlo (MC) method. MC is a model-free method, meaning that we compute the optimal policy without using the model dynamics of the environment. But one problem we face with the MC...