Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
Reinforcement learning : with OpenAI, TensorFlow and Keras using Python
Nandy A., Biswas M., Apress, New York, NY, 2018. 167 pp. Type: Book (978-1-484232-84-2)
Date Reviewed: Oct 11 2018

The success of reinforcement learning (RL) in everything from AlphaGo to intelligent decision making for services in everyday life has made RL a hot topic. The concept has been around since the birth of artificial intelligence (AI) via Turing’s ideas, especially in Marvin Minsky’s vision in The society of mind [1].

Recent advances in deep learning and the drive toward self-driving cars have instigated a number of new studies into various reinforcement algorithms and platforms to test them. Reinforcement learning with OpenAI, TensorFlow, and Keras using Python aims to showcase these applications.

The book has few details on different RL approaches, but offers more on the basic architecture of agents, reward functions and interactions with the environment, and programming exercises.

The book gives a review of installing and setting up various RL libraries and environments such as TensorFlow, Jupyter, and chain RL. Very little is said about big research topics such as swarm learning, dynamic programming, and combinatorial game theory. I think the authors just want to present to readers the possibility of various techniques, but mostly concentrate on implementing some basic examples of games and RL. OpenAI Gym is mentioned as a go-to application for building these systems, but many more examples can also be found on the OpenAI website (https://gym.openai.com/). This book is a good starting point for people trying RL algorithms for the first time, but readers will eventually need more theoretical concepts to actually test and measure the success of their RL algorithms.

There are too many screen shots and too much programming code, with a very limited discussion of theory. It might be a useful tool for PhD students trying to code, but if students want to understand theory and reasoning in RL algorithms, they might need another textbook.

More reviews about this item: Amazon

Reviewer:  Mariam Kiran Review #: CR146271 (1812-0615)
1) Minsky, M. The society of mind. Simon & Schuster, New York, NY, 1986.
Bookmark and Share
  Reviewer Selected
Featured Reviewer
 
 
Python (D.3.2 ... )
 
 
Learning (I.2.6 )
 
Would you recommend this review?
yes
no
Other reviews under "Python": Date
Practical Python
Hetland M., APress, LP, 2002.  648, Type: Book (9781590590065)
Mar 28 2003
Python programming: an introduction to computer science
Zelle J., Franklin B, 2003. Type: Book (9781887902991)
Dec 2 2004
Foundations of Python network programming
Goerzen J., APress, LP, Berkeley, CA, 2004.  512, Type: Book (9781590593714)
Dec 26 2004
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2024 ThinkLoud®
Terms of Use
| Privacy Policy