國立高雄大學圖資館 |

Language: English

Back

Learning to playreinforcement learni...

Plaat, Aske.

Learning to playreinforcement learning and games /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Learning to playby Aske Plaat.
Reminder of title:	reinforcement learning and games /
Author:	Plaat, Aske.
Published:	Cham :Springer International Publishing :2020.
Description:	xiii, 330 p. :ill., digital ;24 cm.
Contained By:	Springer Nature eBook
Subject:	Reinforcement learning.
Online resource:	https://doi.org/10.1007/978-3-030-59238-7
ISBN:	9783030592387$q(electronic bk.)

Learning to playreinforcement learning and games /
Plaat, Aske.

Learning to playreinforcement learning and games /[electronic resource] :by Aske Plaat. - Cham :Springer International Publishing :2020. - xiii, 330 p. :ill., digital ;24 cm.

Introduction -- Intelligence and Games -- Reinforcement Learning -- Heuristic Planning -- Adaptive Sampling -- Function Approximation -- Self-Play -- Conclusion -- App. A, Deep Reinforcement Learning Environments -- App. B, Running Python -- App. C, Tutorial for the Game of Go -- App. D, AlphaGo Technical Details -- References -- List of Figures -- List of Tables -- List of Algorithms -- Index.

In this textbook the author takes as inspiration recent breakthroughs in game playing to explain how and why deep reinforcement learning works. In particular he shows why two-person games of tactics and strategy fascinate scientists, programmers, and game enthusiasts and unite them in a common goal: to create artificial intelligence (AI) After an introduction to the core concepts, environment, and communities of intelligence and games, the book is organized into chapters on reinforcement learning, heuristic planning, adaptive sampling, function approximation, and self-play. The author takes a hands-on approach throughout, with Python code examples and exercises that help the reader understand how AI learns to play. He also supports the main text with detailed pointers to online machine learning frameworks, technical details for AlphaGo, notes on how to play and program Go and chess, and a comprehensive bibliography. The content is class-tested and suitable for advanced undergraduate and graduate courses on artificial intelligence and games. It's also appropriate for self-study by professionals engaged with applications of machine learning and with games development. Finally it's valuable for any reader engaged with the philosophical implications of artificial and general intelligence, games represent a modern Turing test of the power and limitations of AI.

ISBN: 9783030592387$q(electronic bk.)

Standard No.: 10.1007/978-3-030-59238-7doiSubjects--Topical Terms:

349131
Reinforcement learning.

LC Class. No.: Q325.6 / .P53 2020

Dewey Class. No.: 006.31

Learning to playreinforcement learning and games /
LDR:02741nmm a2200325 a 4500 001 589361
003 DE-He213
005 20201121195207.0
006 m d
007 cr nn 008maaau
008 210601s2020 sz s 0 eng d
020 $a 9783030592387$q(electronic bk.)
020 $a 9783030592370$q(paper)
024 7 $a 10.1007/978-3-030-59238-7 $2 doi
035 $a 978-3-030-59238-7
040 $a GP $c GP
041 0 $a eng
050 4 $a Q325.6 $b .P53 2020
072 7 $a UYQ $2 bicssc
072 7 $a COM004000 $2 bisacsh
072 7 $a UYQ $2 thema
082 0 4 $a 006.31 $2 23
090 $a Q325.6 $b .P696 2020
100 1 $a Plaat, Aske. $3 510586
245 1 0 $a Learning to play $h [electronic resource] : $b reinforcement learning and games / $c by Aske Plaat.
260 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2020.
300 $a xiii, 330 p. : $b ill., digital ; $c 24 cm.
505 0 $a Introduction -- Intelligence and Games -- Reinforcement Learning -- Heuristic Planning -- Adaptive Sampling -- Function Approximation -- Self-Play -- Conclusion -- App. A, Deep Reinforcement Learning Environments -- App. B, Running Python -- App. C, Tutorial for the Game of Go -- App. D, AlphaGo Technical Details -- References -- List of Figures -- List of Tables -- List of Algorithms -- Index.
520 $a In this textbook the author takes as inspiration recent breakthroughs in game playing to explain how and why deep reinforcement learning works. In particular he shows why two-person games of tactics and strategy fascinate scientists, programmers, and game enthusiasts and unite them in a common goal: to create artificial intelligence (AI) After an introduction to the core concepts, environment, and communities of intelligence and games, the book is organized into chapters on reinforcement learning, heuristic planning, adaptive sampling, function approximation, and self-play. The author takes a hands-on approach throughout, with Python code examples and exercises that help the reader understand how AI learns to play. He also supports the main text with detailed pointers to online machine learning frameworks, technical details for AlphaGo, notes on how to play and program Go and chess, and a comprehensive bibliography. The content is class-tested and suitable for advanced undergraduate and graduate courses on artificial intelligence and games. It's also appropriate for self-study by professionals engaged with applications of machine learning and with games development. Finally it's valuable for any reader engaged with the philosophical implications of artificial and general intelligence, games represent a modern Turing test of the power and limitations of AI.
650 0 $a Reinforcement learning. $3 349131
650 0 $a Artificial intelligence. $3 194058
650 0 $a Computer games. $3 235432
650 2 4 $a Game Development. $3 761231
650 2 4 $a Popular Culture. $3 763075
650 2 4 $a Media and Communication. $3 742407
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer Nature eBook
856 4 0 $u https://doi.org/10.1007/978-3-030-59238-7
950 $a Computer Science (SpringerNature-11645)