Press release of Impress Holdings Co., Ltd. (2024.09.30) Impress Holdings Co., Ltd. Understand
optimization methods using reinforcement learning from scratch! Published Volume 3 of Problem Solving Series with Python,
“Reinforcement Learning for Optimization” Modern Science Co., Ltd., a member of the Impress Group that publishes specialized books in the field of science and engineering, will publish “Reinforcement Learning for Optimization” (supervisor: Mikio Kubo, author: Kazuhiro Kobayashi) on September 30, 2024. Thank you.
https://prcdn.freetls.fastly.net/release_image/5875/6178/5875-6178-c814c8b7681dff655bf407631b1ff70e-1434×1827.jpg
●Bibliographic information [Series name] Problem solving series using Python Volume 3 [Book title] Reinforcement learning for optimization [Supervision] Mikio Kubo [Author] Kazuhiro Kobayashi [Specifications] B5 variant size, standard size, 204 pages [Base price] 3,200 yen (3,520 yen including tax) [ISBN]978-4-7649-0710-2 C3304 [Product URL]
https://www.kindaikagaku.co.jp/book_list/detail/9784764907102/ ●Content introduction This book introduces the basic concepts and calculation methods of reinforcement learning, and summarizes how to actually implement it using Python. Specifically, it deals with Markov decision processes, value functions, policy evaluation, policy iteration, value iteration, Monte Carlo evaluation, SARSA, and Q-learning. Most of the content is written in such a way that it can be easily understood by those with a basic knowledge of mathematics, and the book is designed to make it easier for the reader to learn by repeating explanations and reposting formulas that have already been published. A comprehensive book that explains in detail everything from the basics of Python to the use of reinforcement learning. ●Author introduction Kazuhiro Kobayashi March 2003 Completed master’s course at Keio University Graduate School of Letters 1998 Graduated from Department of Mathematical Engineering, Faculty of Engineering, University of Tokyo 2000 Completed master’s program, Department of Mathematical Engineering, Graduate School of Engineering, University of Tokyo, Master of Engineering (Engineering) 2009 Ph.D. (Science) Currently Associate Professor, Faculty of Science and Engineering, Aoyama Gakuin University Major books “Supply Chain Risk Management and Humanitarian Assistance Logistics” (co-author), Kindai Kagakusha (2015) “Basics of applied nautical mechanics” (co-author), Seizando Shoten (2015) “Business Analytics with Python Language | Optimization, Statistical Analysis, and Machine Learning for Practitioners” (co-author), Kindai Kagakusha (2016) “Introduction to optimization problems” (Problem solving series with Python 2), Kindai Kagakusha (2020) ●Table of contents Chapter 1: Building an environment for reinforcement learning with Python 1.1 How to use online services 1.2 How to set up the execution environment on your computer 1.3 Installing packages 1.4 Execution environment Chapter 2 Python Basics 2.1 Data structure 2.2 Scientific calculation package NumPy 2.3 Conditional branching 2.4 Iterative processing 2.5 Pseudo-random number generation package random 2.6 Visualization library Matplotlib 2.7 Functions 2.8 Comprehensions Chapter 3 Overview of Reinforcement Learning Chapter 4 Markov Decision Process 4.1 Markov property 4.2 Transition probability matrix 4.3 Markov process 4.4 Markov reward process 4.5 Return 4.6 Value function 4.7 Strategies 4.8 Markov decision process Chapter 5 Dynamic Programming 5.1 Example 1: Sum of integers 5.2 Example 2: Shortest path problem 5.3 Evaluation of value function by dynamic programming 5.4 Policy evaluation 5.5 Policy improvement 5.6 Strategy Iteration 5.7 Value Iteration Chapter 6 Monte Carlo Learning 6.1 Full width search and sample search 6.2 Monte Carlo policy evaluation 6.3 First-visit Monte Carlo policy evaluation 6.4 Every-visit Monte Carlo policy evaluation 6.5 Incremental calculation of average Chapter 7 Temporal Difference Learning 7.1 TD(0) learning 7.2 On-policy learning and off-policy learning 7.3 On-policy Monte Carlo learning 7.4 On-Policy TD Learning – SARSA 7.5 Off-policy TD learning – Q learning [Kindaikagaku Co., Ltd.]
https://www.kindaikagaku.co.jp Kindai Kagakusha Co., Ltd.
(Headquarters: Chiyoda-ku, Tokyo, Representative Director and President: Hiroaki Otsuka) was founded in 1959. We are developing a publishing business that covers a wide range of specialized fields of science and engineering, including academic books centered on mathematics, mathematical sciences, information science, and information engineering, as well as textbooks for science and engineering universities. In order to meet modern needs that require not only basic knowledge of natural science but also its advanced use, we cover a wide range of subjects, from classics to the latest interdisciplinary fields. In addition, we collaborate with major academic societies, associations, and prominent research institutions to pursue an academic level that will become a global standard. [Impress Group]
https://www.impressholdings.com A media group whose holding company is Impress Holdings Co., Ltd. (Headquarters: Chiyoda-ku, Tokyo, Representative Director: Daisuke Matsumoto, Stock Code: TSE 1st Section 9479). We are developing highly specialized media & services and solution businesses with the main themes of “IT,” “music,” “design,” “mountains/nature,” “aviation/railway,” “mobile services,” and “academic/science and engineering.” Furthermore, we also develop and operate content business platforms. [Contact information] Kindai Kagakusha Co., Ltd. TEL: 03-6837-4828 Email: reader@kindaikagaku.co.jp
