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

Deep deterministic policy gradient

DDPG is an off-policy, model-free algorithm, designed for environments where the action space is continuous. In the previous chapter, we learned how the actor-critic method works. DDPG is an actor-critic method where the actor estimates the policy using the policy gradient, and the critic evaluates the policy produced by the actor using the Q function.

DDPG uses the policy network as an actor and deep Q network as a critic. One important difference between the DPPG and actor-critic algorithms we learned in the previous chapter is that DDPG tries to learn a deterministic policy instead of a stochastic policy.

First, we will get an intuitive understanding of how DDPG works and then we will look into the algorithm in detail.

An overview of DDPG

DDPG is an actor-critic method that takes advantage of both the policy-based method and the value-based method. It uses a deterministic policy instead of a stochastic policy .

...