Learning Representation and Control in Markov Decision Processes

Name: Learning Representation and Control in Markov Decision Processes
Price: 100.7 USD
Availability: InStock
ISBN: 9781601982384

ISBN-10: 1601982380

ISBN-13: 9781601982384

Edition: 2009

Authors: Sridhar Mahadevan

List price: $110.00

30 day, 100% satisfaction guarantee!

Marketplace

1 new & used from $100.70

what's this?

Rush Rewards U
Members Receive:

You have reached 400 XP and carrot coins. That is the daily max!

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…

Book details

List price: $110.00
Copyright year: 2009
Publisher: Now Publishers
Publication date: 6/2/2009
Binding: Paperback
Pages: 184
Size: 6.14" wide x 9.21" long x 0.39" tall
Weight: 0.594
Language: English