Vous voulez voir cette page en français ? Cliquez ici.


or
Sign in to turn on 1-Click ordering.
More Buying Choices
Have one to sell? Sell yours here
Tell the Publisher!
I'd like to read this book on Kindle

Don't have a Kindle? Get your Kindle here, or download a FREE Kindle Reading App.

Reinforcement Learning Algorithms for Markov Decision Processes [Paperback]

Csaba Szepesvari , Ronald Brachman , Thomas G. Dietterich

List Price: CDN$ 39.50
Price: CDN$ 35.62 & FREE Shipping. Details
You Save: CDN$ 3.88 (10%)
o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o
Usually ships within 3 to 5 weeks.
Ships from and sold by Amazon.ca. Gift-wrap available.

Book Description

Aug. 1 2010 Synthesis Lectures on Artificial Intelligence and Machine Le
Reinforcement learning is a learning paradigm concerned with learning to control a system so as to maximize a numerical performance measure that expresses a long-term objective. What distinguishes reinforcement learning from supervised learning is that only partial feedback is given to the learner about the learner's predictions. Further, the predictions may have long term effects through influencing the future state of the controlled system. Thus, time plays a special role. The goal in reinforcement learning is to develop efficient learning algorithms, as well as to understand the algorithms' merits and limitations. Reinforcement learning is of great interest because of the large number of practical applications that it can be used to address, ranging from problems in artificial intelligence to operations research or control engineering. In this book, we focus on those algorithms of reinforcement learning that build on the powerful theory of dynamic programming.We give a fairly comprehensive catalog of learning problems, describe the core ideas, note a large number of state of the art algorithms, followed by the discussion of their theoretical properties and limitations.

Customers Who Bought This Item Also Bought


Product Details

  • Paperback: 103 pages
  • Publisher: Morgan & Claypool Publishers (Aug. 1 2010)
  • Language: English
  • ISBN-10: 1608454924
  • ISBN-13: 978-1608454921
  • Product Dimensions: 23.5 x 19 x 0.6 cm
  • Shipping Weight: 200 g
  • Amazon Bestsellers Rank: #837,961 in Books (See Top 100 in Books)

Sell a Digital Version of This Book in the Kindle Store

If you are a publisher or author and hold the digital rights to a book, you can sell a digital version of it in our Kindle Store. Learn more

Customer Reviews

There are no customer reviews yet on Amazon.ca
5 star
4 star
3 star
2 star
1 star
Most Helpful Customer Reviews on Amazon.com (beta)
Amazon.com: 5.0 out of 5 stars  1 review
1 of 1 people found the following review helpful
5.0 out of 5 stars Fantastic book April 5 2013
By Amazon Customer - Published on Amazon.com
Format:Paperback|Verified Purchase
The is an extraordinary resource for a graduate student. Szepesvari reviews the current place of the literature, gives a very quick but still thorough introduction to reinforcement learning, and includes algorithms for quite a few methods. This is everything a graduate student could ask for in a text. And in 100 pages! Fantastic.

I almost docked one star because the book doesn't have an index, but then remembered that you can get a pdf version of this book straight from the authors website -- which of course you can then simply search for the term you want. That alone makes me want to give it 6 starts. Ah well, I will have to settle for 5 and shining review.
ARRAY(0xac6d06cc)

Look for similar items by category


Feedback