You're reading from TensorFlow Reinforcement Learning Quick Start Guide Get up and running with training and deploying intelligent, self-learning agents using Python

Product type Paperback

Published in Mar 2019

Publisher Packt

ISBN-13 9781789533583

Length 184 pages

Edition 1st Edition

Languages

Python

Tools

TensorFlow

Concepts

Reinforcement Learning

Author (1):

Kaushik Balakrishnan

View More author details

Table of Contents (11) Chapters

Preface

1. Up and Running with Reinforcement Learning FREE CHAPTER

2. Temporal Difference, SARSA, and Q-Learning

3. Deep Q-Network

4. Double DQN, Dueling Architectures, and Rainbow

5. Deep Deterministic Policy Gradient

6. Asynchronous Methods - A3C and A2C

7. Trust Region Policy Optimization and Proximal Policy Optimization

8. Deep RL Applied to Autonomous Driving

9. Assessment

10. Other Books You May Enjoy

Leave a review - let other readers know what you think

Questions

Can we apply Adam or SGD optimization in TRPO?
What is the role of the entropy term in the policy optimization?
Why do we clip the policy ratio? What will happen if the clipping parameter epsilon is large?
Why do we use the tanh activation function for mu and softplus for sigma? Can we use the tanh activation function for sigma?
Does reward shaping always help in the training?
Do we need reward shaping when we test an already trained agent?

The rest of the chapter is locked

A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.

Unlock this book and the full library FREE for 7 days

Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of

Start free trial

Renews at $19.99/month. Cancel anytime

Authors (1)

Balakrishnan

Kaushik Balakrishnan works for BMW in Silicon Valley, and applies reinforcement learning, machine learning, and computer vision to solve problems in autonomous driving. Previously, he also worked at Ford Motor Company and NASA Jet Propulsion Laboratory. His primary expertise is in machine learning, computer vision, and high-performance computing, and he has worked on several projects involving both research and industrial applications. He has also worked on numerical simulations of rocket landings on planetary surfaces, and for this he developed several high-fidelity models that run efficiently on supercomputers. He holds a PhD in aerospace engineering from the Georgia Institute of Technology in Atlanta, Georgia.

See other products by Balakrishnan