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

Summary

We started off the chapter by learning that with value-based methods, we extract the optimal policy from the optimal Q function (Q values). Then we learned that it is difficult to compute the Q function when our action space is continuous. We can discretize the action space; however, discretization is not always desirable, and it leads to the loss of several important features and an action space with a huge set of actions.

So, we resorted to the policy-based method. In the policy-based method, we compute the optimal policy without the Q function. We learned about one of the most popular policy-based methods called the policy gradient, in which we find the optimal policy directly by parameterizing the policy using some parameter .

We also learned that in the policy gradient method, we select actions based on the action probability distribution given by the network, and if we win the episode, that is, if we get a high return, then we assign high probabilities to all...