國立虎尾科技大學 |

Deep reinforcement learning = frontiers of artificial intelligence /

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Deep reinforcement learning/ by Mohit Sewak.
Reminder of title:	frontiers of artificial intelligence /
Author:	Sewak, Mohit.
Published:	Singapore :Springer Singapore : : 2019.,
Description:	xvii, 203 p. :ill. (some col.), digital ; : 24 cm.;
Contained By:	Springer eBooks
Subject:	Reinforcement learning. -
Online resource:	https://doi.org/10.1007/978-981-13-8285-7
ISBN:	9789811382857

Deep reinforcement learning = frontiers of artificial intelligence /
Sewak, Mohit.

Deep reinforcement learningfrontiers of artificial intelligence /[electronic resource] :by Mohit Sewak. - Singapore :Springer Singapore :2019. - xvii, 203 p. :ill. (some col.), digital ;24 cm.

Introduction to Reinforcement Learning -- Mathematical and Algorithmic understanding of Reinforcement Learning -- Coding the Environment and MDP Solution -- Temporal Difference Learning, SARSA, and Q Learning -- Q Learning in Code -- Introduction to Deep Learning -- Implementation Resources -- Deep Q Network (DQN), Double DQN and Dueling DQN -- Double DQN in Code -- Policy-Based Reinforcement Learning Approaches -- Actor-Critic Models & the A3C -- A3C in Code -- Deterministic Policy Gradient and the DDPG -- DDPG in Code.

This book starts by presenting the basics of reinforcement learning using highly intuitive and easy-to-understand examples and applications, and then introduces the cutting-edge research advances that make reinforcement learning capable of out-performing most state-of-art systems, and even humans in a number of applications. The book not only equips readers with an understanding of multiple advanced and innovative algorithms, but also prepares them to implement systems such as those created by Google Deep Mind in actual code. This book is intended for readers who want to both understand and apply advanced concepts in a field that combines the best of two worlds - deep learning and reinforcement learning - to tap the potential of 'advanced artificial intelligence' for creating real-world applications and game-winning algorithms.

ISBN: 9789811382857

Standard No.: 10.1007/978-981-13-8285-7doiSubjects--Topical Terms:

815404
Reinforcement learning.

LC Class. No.: Q325.6 / .S49 2019

Dewey Class. No.: 005.11

Deep reinforcement learning = frontiers of artificial intelligence /
LDR:02350nam a2200325 a 4500 001 941018
003 DE-He213
005 20190627193138.0
006 m d
007 cr nn 008maaau
008 200417s2019 si s 0 eng d
020 $a 9789811382857 $q (electronic bk.)
020 $a 9789811382840 $q (paper)
024 7 $a 10.1007/978-981-13-8285-7 $2 doi
035 $a 978-981-13-8285-7
040 $a GP $c GP
041 0 $a eng
050 4 $a Q325.6 $b .S49 2019
072 7 $a UM $2 bicssc
072 7 $a COM051000 $2 bisacsh
072 7 $a UM $2 thema
082 0 4 $a 005.11 $2 23
090 $a Q325.6 $b .S512 2019
100 1 $a Sewak, Mohit. $3 1228010
245 1 0 $a Deep reinforcement learning $h [electronic resource] : $b frontiers of artificial intelligence / $c by Mohit Sewak.
260 $a Singapore : $c 2019. $b Springer Singapore : $b Imprint: Springer,
300 $a xvii, 203 p. : $b ill. (some col.), digital ; $c 24 cm.
505 0 $a Introduction to Reinforcement Learning -- Mathematical and Algorithmic understanding of Reinforcement Learning -- Coding the Environment and MDP Solution -- Temporal Difference Learning, SARSA, and Q Learning -- Q Learning in Code -- Introduction to Deep Learning -- Implementation Resources -- Deep Q Network (DQN), Double DQN and Dueling DQN -- Double DQN in Code -- Policy-Based Reinforcement Learning Approaches -- Actor-Critic Models & the A3C -- A3C in Code -- Deterministic Policy Gradient and the DDPG -- DDPG in Code.
520 $a This book starts by presenting the basics of reinforcement learning using highly intuitive and easy-to-understand examples and applications, and then introduces the cutting-edge research advances that make reinforcement learning capable of out-performing most state-of-art systems, and even humans in a number of applications. The book not only equips readers with an understanding of multiple advanced and innovative algorithms, but also prepares them to implement systems such as those created by Google Deep Mind in actual code. This book is intended for readers who want to both understand and apply advanced concepts in a field that combines the best of two worlds - deep learning and reinforcement learning - to tap the potential of 'advanced artificial intelligence' for creating real-world applications and game-winning algorithms.
650 0 $a Reinforcement learning. $3 815404
650 1 4 $a Programming Techniques. $3 669781
650 2 4 $a Artificial Intelligence. $3 646849
650 2 4 $a Algorithm Analysis and Problem Complexity. $3 593923
650 2 4 $a Cryptology. $3 1211076
710 2 $a SpringerLink (Online service) $3 593884
773 0 $t Springer eBooks
856 4 0 $u https://doi.org/10.1007/978-981-13-8285-7
950 $a Computer Science (Springer-11645)