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

What is DQN?

The objective of reinforcement learning is to find the optimal policy, that is, the policy that gives us the maximum return (the sum of rewards of the episode). In order to compute the policy, first we compute the Q function. Once we have the Q function, then we extract the policy by selecting an action in each state that has the maximum Q value. For instance, let's suppose we have two states A and B and our action space consists of two actions; let the actions be up and down. So, in order to find which action to perform in state A and B, first we compute the Q value of all state-action pairs, as Table 9.1 shows:

Table 9.1: Q-value of state-action pairs

Once we have the Q value of all state-action pairs, then we select the action in each state that has the maximum Q value. So, we select the action up in state A and down in state B as they have the maximum Q value. We improve the Q function on every iteration and once we have the optimal Q function, then...