Recently Viewed

New

Learning Representation and Control in Markov Decision Processes: New Frontiers by Sridhar Mahadevan 9781601982384

No reviews yet Write a Review
RRP: £99.50
Booksplease Price: £89.09
Booksplease saves you

  Delivery: We ship to over 200 countries from the UK
  Range: Millions of books available
  Reviews: Booksplease rated "Excellent" on Trustpilot

  FREE UK DELIVERY: When you buy 3 or more books on Booksplease - Use code: FREEUKDELIVERY in your cart!

SKU:
9781601982384
MPN:
9781601982384
Available from Booksplease!
Availability: Usually dispatched within 5 working days

Frequently Bought Together:

Total: Inc. VAT
Total: Ex. VAT

Description

Learning Representation and Control in Markov Decision Processes describes methods for automatically compressing Markov decision processes (MDPs) by learning a low-dimensional linear approximation defined by an orthogonal set of basis functions. A unique feature of the text is the use of Laplacian operators, whose matrix representations have non-positive off-diagonal elements and zero row sums. The generalized inverses of Laplacian operators, in particular the Drazin inverse, are shown to be useful in the exact and approximate solution of MDPs. The author goes on to describe a broad framework for solving MDPs, generically referred to as representation policy iteration (RPI), where both the basis function representations for approximation of value functions as well as the optimal policy within their linear span are simultaneously learned. Basis functions are constructed by diagonalizing a Laplacian operator or by dilating the reward function or an initial set of bases by powers of the operator. The idea of decomposing an operator by finding its invariant subspaces is shown to be an important principle in constructing low-dimensional representations of MDPs. Theoretical properties of these approaches are discussed, and they are also compared experimentally on a variety of discrete and continuous MDPs. Finally, challenges for further research are briefly outlined. This is a timely exposition of a topic with broad interest within machine learning and beyond.

Book Information
ISBN 9781601982384
Author Sridhar Mahadevan
Format Paperback
Page Count 184
Imprint now publishers Inc
Publisher now publishers Inc
Weight(grams) 268g

Reviews

No reviews yet Write a Review

Booksplease  Reviews


J - United Kingdom

Fast and efficient way to choose and receive books

This is my second experience using Booksplease. Both orders dealt with very quickly and despatched. Now waiting for my next read to drop through the letterbox.

J - United Kingdom

T - United States

Will definitely use again!

Great experience and I have zero concerns. They communicated through the shipping process and if there was any hiccups in it, they let me know. Books arrived in perfect condition as well as being fairly priced. 10/10 recommend. I will definitely shop here again!

T - United States

R - Spain

The shipping was just superior

The shipping was just superior; not even one of the books was in contact with the shipping box -anywhere-, not even a corner or the bottom, so all the books arrived in perfect condition. The international shipping took around 2 weeks, so pretty great too.

R - Spain

J - United Kingdom

Found a hard to get book…

Finding a hard to get book on Booksplease and with it not being an over inflated price was great. Ordering was really easy with updates on despatch. The book was packaged well and in great condition. I will certainly use them again.

J - United Kingdom