國立高雄大學圖資館 |

Language: English

Back

Reinforcement learningtheory and python implementation /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Reinforcement learningby Zhiqing Xiao.
Reminder of title:	theory and python implementation /
Author:	Xiao, Zhiqing.
Published:	Singapore :Springer Nature Singapore :2024.
Description:	xxii, 559 p. :ill., digital ;24 cm.
Contained By:	Springer Nature eBook
Subject:	Reinforcement learning.
Online resource:	https://doi.org/10.1007/978-981-19-4933-3
ISBN:	9789811949333$q(electronic bk.)

Reinforcement learningtheory and python implementation /
Xiao, Zhiqing.

Reinforcement learningtheory and python implementation /[electronic resource] :by Zhiqing Xiao. - Singapore :Springer Nature Singapore :2024. - xxii, 559 p. :ill., digital ;24 cm.

Chapter 1. Introduction of Reinforcement Learning (RL) -- Chapter 2. MDP: Markov Decision Process -- Chapter 3. Model-based Numerical Iteration -- Chapter 4. MC: Monte Carlo Learning -- Chapter 5. TD: Temporal Difference Learning -- Chapter 6. Function Approximation -- Chapter 7. PG: Policy Gradient -- Chapter 8. AC: Actor-Critic -- Chapter 9. DPG: Deterministic Policy Gradient -- Chapter 10. Maximum-Entropy RL -- Chapter 11. Policy-based Gradient-Free Algorithms -- Chapter 12. Distributional RL -- Chapter 13. Minimize Regret -- Chapter 14. Tree Search -- Chapter 15. More Agent-Environment Interfaces -- Chapter 16. Learn from Feedback and Imitation Learning.

Reinforcement Learning: Theory and Python Implementation is a tutorial book on reinforcement learning, with explanations of both theory and applications. Starting from a uniform mathematical framework, this book derives the theory of modern reinforcement learning systematically and introduces all mainstream reinforcement learning algorithms such as PPO, SAC, and MuZero. It also covers key technologies of GPT training such as RLHF, IRL, and PbRL. Every chapter is accompanied by high-quality implementations, and all implementations of deep reinforcement learning algorithms are with both TensorFlow and PyTorch. Codes can be found on GitHub along with their results and are runnable on a conventional laptop with either Windows, macOS, or Linux. This book is intended for readers who want to learn reinforcement learning systematically and apply reinforcement learning to practical applications. It is also ideal to academical researchers who seek theoretical foundation or algorithm enhancement in their cutting-edge AI research.

ISBN: 9789811949333$q(electronic bk.)

Standard No.: 10.1007/978-981-19-4933-3doiSubjects--Topical Terms:

349131
Reinforcement learning.

LC Class. No.: Q325.6

Dewey Class. No.: 006.31

Reinforcement learningtheory and python implementation /
LDR:02669nmm a2200325 a 4500 001 669152
003 DE-He213
005 20240929130232.0
006 m d
007 cr nn 008maaau
008 250120s2024 si s 0 eng d
020 $a 9789811949333$q(electronic bk.)
020 $a 9789811949326$q(paper)
024 7 $a 10.1007/978-981-19-4933-3 $2 doi
035 $a 978-981-19-4933-3
040 $a GP $c GP
041 0 $a eng
050 4 $a Q325.6
072 7 $a UYQM $2 bicssc
072 7 $a MAT029000 $2 bisacsh
072 7 $a UYQM $2 thema
082 0 4 $a 006.31 $2 23
090 $a Q325.6 $b .X6 2024
100 1 $a Xiao, Zhiqing. $3 982096
245 1 0 $a Reinforcement learning $h [electronic resource] : $b theory and python implementation / $c by Zhiqing Xiao.
260 $a Singapore : $b Springer Nature Singapore : $b Imprint: Springer, $c 2024.
300 $a xxii, 559 p. : $b ill., digital ; $c 24 cm.
505 0 $a Chapter 1. Introduction of Reinforcement Learning (RL) -- Chapter 2. MDP: Markov Decision Process -- Chapter 3. Model-based Numerical Iteration -- Chapter 4. MC: Monte Carlo Learning -- Chapter 5. TD: Temporal Difference Learning -- Chapter 6. Function Approximation -- Chapter 7. PG: Policy Gradient -- Chapter 8. AC: Actor-Critic -- Chapter 9. DPG: Deterministic Policy Gradient -- Chapter 10. Maximum-Entropy RL -- Chapter 11. Policy-based Gradient-Free Algorithms -- Chapter 12. Distributional RL -- Chapter 13. Minimize Regret -- Chapter 14. Tree Search -- Chapter 15. More Agent-Environment Interfaces -- Chapter 16. Learn from Feedback and Imitation Learning.
520 $a Reinforcement Learning: Theory and Python Implementation is a tutorial book on reinforcement learning, with explanations of both theory and applications. Starting from a uniform mathematical framework, this book derives the theory of modern reinforcement learning systematically and introduces all mainstream reinforcement learning algorithms such as PPO, SAC, and MuZero. It also covers key technologies of GPT training such as RLHF, IRL, and PbRL. Every chapter is accompanied by high-quality implementations, and all implementations of deep reinforcement learning algorithms are with both TensorFlow and PyTorch. Codes can be found on GitHub along with their results and are runnable on a conventional laptop with either Windows, macOS, or Linux. This book is intended for readers who want to learn reinforcement learning systematically and apply reinforcement learning to practical applications. It is also ideal to academical researchers who seek theoretical foundation or algorithm enhancement in their cutting-edge AI research.
650 0 $a Reinforcement learning. $3 349131
650 1 4 $a Machine Learning. $3 833608
650 2 4 $a Artificial Intelligence. $3 212515
650 2 4 $a Robotics. $3 181952
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer Nature eBook
856 4 0 $u https://doi.org/10.1007/978-981-19-4933-3
950 $a Computer Science (SpringerNature-11645)