Reinforcement learning and optimal control

By:

Bertsekas, Dimitri P

Material type: Text

TextPublication details: Massachusetts Athena Scientific 2019Description: xiv, 373pISBN:

9781886529397 (hb.)

Subject(s):

DDC classification:

519.703 BER

Summary: This book considers large and challenging multistage decision problems, which can be solved in principle by dynamic programming (DP), but their exact solution is computationally intractable. We discuss solution methods that rely on approximations to produce suboptimal policies with adequate performance. These methods are collectively known by several essentially equivalent names: reinforcement learning, approximate dynamic programming, and neuro-dynamic programming. They have been at the forefront of research for the last 25 years, and they underlie, among others, the recent impressive successes of self-learning in the context of games such as chess and Go.

Tags from this library: No tags from this library for this title. Log in to add tags.

Average rating: 0.0 (0 votes)

Holdings
Item type	Current library	Collection	Call number	Status	Date due	Barcode
Book	Plaksha University Library	Mathematics	519.703 BER (Browse shelf(Opens below))	Available		003011
Book	Plaksha University Library	Mathematics	519.703 BER (Browse shelf(Opens below))	Available		003012

Browsing Plaksha University Library shelves, Collection: Mathematics Close shelf browser (Hides shelf browser)

Previous								Next
Previous	519.703 BER Dynamic programming and optimal control	519.703 BER Dynamic programming and optimal control : approximate dynamic programming	519.703 BER Dynamic programming and optimal control : approximate dynamic programming	519.703 BER Reinforcement learning and optimal control	519.703 BER Reinforcement learning and optimal control	519.703 POW Approximate dynamic programming : solving the curses of dimensionality	519.703 POW Approximate dynamic programming : solving the curses of dimensionality	Next

http://www.athenasc.com/rlbook_athena.html

This book considers large and challenging multistage decision problems, which can be solved in principle by dynamic programming (DP), but their exact solution is computationally intractable. We discuss solution methods that rely on approximations to produce suboptimal policies with adequate performance. These methods are collectively known by several essentially equivalent names: reinforcement learning, approximate dynamic programming, and neuro-dynamic programming. They have been at the forefront of research for the last 25 years, and they underlie, among others, the recent impressive successes of self-learning in the context of games such as chess and Go.

There are no comments on this title.

to post a comment.