國立高雄大學圖資館 |

登入

回首頁

Control systems and reinforcement learning

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Control systems and reinforcement learningSean Meyn.
作者:	Meyn, Sean.
出版者:	Cambridge :Cambridge University Press,2022.
面頁冊數:	xv, 435 p. :ill., digital ;25 cm.
附註:	Title from publisher's bibliographic system (viewed on 07 Apr 2022).
標題:	Reinforcement learning.
電子資源:	https://doi.org/10.1017/9781009051873
ISBN:	9781009051873$q(electronic bk.)

Control systems and reinforcement learning
Meyn, Sean.

Control systems and reinforcement learning[electronic resource] /Sean Meyn. - Cambridge :Cambridge University Press,2022. - xv, 435 p. :ill., digital ;25 cm.

Title from publisher's bibliographic system (viewed on 07 Apr 2022).

A high school student can create deep Q-learning code to control her robot, without any understanding of the meaning of 'deep' or 'Q', or why the code sometimes fails. This book is designed to explain the science behind reinforcement learning and optimal control in a way that is accessible to students with a background in calculus and matrix algebra. A unique focus is algorithm design to obtain the fastest possible speed of convergence for learning algorithms, along with insight into why reinforcement learning sometimes fails. Advanced stochastic process theory is avoided at the start by substituting random exploration with more intuitive deterministic probing for learning. Once these ideas are understood, it is not difficult to master techniques rooted in stochastic control. These topics are covered in the second part of the book, starting with Markov chain theory and ending with a fresh look at actor-critic methods for reinforcement learning.

ISBN: 9781009051873$q(electronic bk.)Subjects--Topical Terms:

349131
Reinforcement learning.

LC Class. No.: Q325.6 / .M49 2022

Dewey Class. No.: 006.31

Control systems and reinforcement learning
LDR:01742nmm a2200241 a 4500 001 626803
003 UkCbUP
005 20220609101243.0
006 m d
007 cr nn 008maaau
008 230118s2022 enk o 1 0 eng d
020 $a 9781009051873$q(electronic bk.)
020 $a 9781316511961$q(hardback)
035 $a CR9781009051873
040 $a UkCbUP $b eng $c UkCbUP $d GP
050 4 $a Q325.6 $b .M49 2022
082 0 4 $a 006.31 $2 23
090 $a Q325.6 $b .M614 2022
100 1 $a Meyn, Sean. $3 819190
245 1 0 $a Control systems and reinforcement learning $h [electronic resource] / $c Sean Meyn.
260 $a Cambridge : $b Cambridge University Press, $c 2022.
300 $a xv, 435 p. : $b ill., digital ; $c 25 cm.
500 $a Title from publisher's bibliographic system (viewed on 07 Apr 2022).
520 $a A high school student can create deep Q-learning code to control her robot, without any understanding of the meaning of 'deep' or 'Q', or why the code sometimes fails. This book is designed to explain the science behind reinforcement learning and optimal control in a way that is accessible to students with a background in calculus and matrix algebra. A unique focus is algorithm design to obtain the fastest possible speed of convergence for learning algorithms, along with insight into why reinforcement learning sometimes fails. Advanced stochastic process theory is avoided at the start by substituting random exploration with more intuitive deterministic probing for learning. Once these ideas are understood, it is not difficult to master techniques rooted in stochastic control. These topics are covered in the second part of the book, starting with Markov chain theory and ending with a fresh look at actor-critic methods for reinforcement learning.
650 0 $a Reinforcement learning. $3 349131
650 0 $a Mathematical optimization. $3 183292
650 0 $a Control theory. $3 182248
856 4 0 $u https://doi.org/10.1017/9781009051873