建國科技大學圖書館 |

語系: 繁體中文

說明(常見問題)

圖書館個人資料蒐集告知聲明

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Mastering reinforcement learning wit...

Bilgin, Enes.

Mastering reinforcement learning with Python : build next-generation, self-learning models using reinforcement learning techniques and best practices

紀錄類型:	書目-語言資料,印刷品 : 單行本
副題名:	build next-generation, self-learning models using reinforcement learning techniques and best practices
作者:	BilginEnes.,
出版地:	Birmingham, UK
出版者:	Packt Publishing;
出版年:	c2020.
面頁冊數:	xvi, 525 p.ill. : 24 cm.;
標題:	Reinforcement learning. -
標題:	Python (Computer program language) -
附註:	Includes index.
摘要註:	Reinforcement learning (RL) is a field of artificial intelligence (AI) used for creating self-learning autonomous agents. Building on a strong theoretical foundation, this book takes a practical approach and uses examples inspired by real-world industry problems to teach you about state-of-the-art RL. Starting with bandit problems, Markov decision processes, and dynamic programming, the book provides an in-depth review of the classical RL techniques, including Monte Carlo methods and temporal-difference learning. After that, you will learn about deep Q-learning, policy gradient algorithms, actor-critic methods, model-based methods, and multi-agent RL. Then, the book will introduce you to some of the key approaches behind the most successful RL implementations, such as domain randomization and curiosity-driven learning. As you advance, you'll explore many novel algorithms with advanced implementations using modern Python libraries such as TensorFlow and Ray's RLib package. You'll also find out how to implement RL in areas such as robotics, supply chain management, marketing, finance, smart cities, and cybersecurity, while assessing the trade-offs between different approaches and avoiding common pitfalls. By the end of this book, you'll have mastered how to train and deploy your own RL agents for solving RL problems.
ISBN:	9781838644147
內容註:	Section 1: Reinforcement learning foundations. 1. Introduction to reinforcement learning 2. Multi-armed bandits 3. Contextual bandits 4. Makings of the markov decision process 5. Solving the reinforcement learning problem Section 2: Deep reinforcement learning. 6. Deep Q-learning at Scale 7. Policy-based methods 8. Model-based methods 9. Multi-agent reinforcement learning Section 3: Advanced topics in RL. 10. Machine learning 11. Generalization and domain randomization 12. Meta-reinforcement learning 13. Other advanced topics Section 4: Applications of RL. 14. Autonomous systems 15. Supply chain management 16. Marketing, personalization and finance 17. Smart city and cybersecurity 18. Challenges and future directions in reinforcement learning.

Mastering reinforcement learning with Python : build next-generation, self-learning models using reinforcement learning techniques and best practices
Bilgin, Enes.

Mastering reinforcement learning with Python : build next-generation, self-learning models using reinforcement learning techniques and best practices / Enes Bilgin. - Birmingham, UK : Packt Publishing, c2020.. - xvi, 525 p. ; ill. ; 24 cm..
Section 1: Reinforcement learning foundations..
Includes index..
ISBN 9781838644147ISBN 1838644148
Reinforcement learning.Python (Computer program language)

Mastering reinforcement learning with Python : build next-generation, self-learning models using reinforcement learning techniques and best practices
LDR:02824cam a2200217 450 001 396455
010 1 $a 9781838644147 $b pbk. $d NT1252
010 1 $a 1838644148 $b pbk.
010 1 $z 9781838648497 $b PDF ebk.
100 $a 20211120d2020 k y0engy50 b
101 0 $a eng
102 $a gb
105 $a a z 001yy
200 1 $a Mastering reinforcement learning with Python $e build next-generation, self-learning models using reinforcement learning techniques and best practices $f Enes Bilgin.
210 $a Birmingham, UK $c Packt Publishing $d c2020.
215 1 $a xvi, 525 p. $c ill. $d 24 cm.
300 $a Includes index.
327 1 $a Section 1: Reinforcement learning foundations. $a 1. Introduction to reinforcement learning $a 2. Multi-armed bandits $a 3. Contextual bandits $a 4. Makings of the markov decision process $a 5. Solving the reinforcement learning problem $a Section 2: Deep reinforcement learning. $a 6. Deep Q-learning at Scale $a 7. Policy-based methods $a 8. Model-based methods $a 9. Multi-agent reinforcement learning $a Section 3: Advanced topics in RL. $a 10. Machine learning $a 11. Generalization and domain randomization $a 12. Meta-reinforcement learning $a 13. Other advanced topics $a Section 4: Applications of RL. $a 14. Autonomous systems $a 15. Supply chain management $a 16. Marketing, personalization and finance $a 17. Smart city and cybersecurity $a 18. Challenges and future directions in reinforcement learning.
330 $a Reinforcement learning (RL) is a field of artificial intelligence (AI) used for creating self-learning autonomous agents. Building on a strong theoretical foundation, this book takes a practical approach and uses examples inspired by real-world industry problems to teach you about state-of-the-art RL. Starting with bandit problems, Markov decision processes, and dynamic programming, the book provides an in-depth review of the classical RL techniques, including Monte Carlo methods and temporal-difference learning. After that, you will learn about deep Q-learning, policy gradient algorithms, actor-critic methods, model-based methods, and multi-agent RL. Then, the book will introduce you to some of the key approaches behind the most successful RL implementations, such as domain randomization and curiosity-driven learning. As you advance, you'll explore many novel algorithms with advanced implementations using modern Python libraries such as TensorFlow and Ray's RLib package. You'll also find out how to implement RL in areas such as robotics, supply chain management, marketing, finance, smart cities, and cybersecurity, while assessing the trade-offs between different approaches and avoiding common pitfalls. By the end of this book, you'll have mastered how to train and deploy your own RL agents for solving RL problems.
517 1 $a Reinforcement learning with Python $z eng
606 $a Reinforcement learning. $2 lc $3 389115
606 $a Python (Computer program language) $2 lc $3 255069
676 $a 006.31 $v 23
700 1 $a Bilgin $b Enes. $3 389114
801 0 $a cw $b CTU $c 20211120 $g AACR2