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: £84.43
Booksplease saves you 15%

  Bookmarks: Included free with every order
  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 - Use code: FREEUKDELIVERY in your cart!

SKU:
9781601982384
MPN:
9781601982384
Available from Booksplease!
Global delivery available
Global delivery available
Global delivery available
Global delivery available
Global delivery available
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