





作者:赵世钰
定价:118元
印次:1-2
ISBN:9787302658528
出版日期:2024.07.01
印刷日期:2025.03.17
图书责编:郭赛
图书分类:零售
"本书从强化学习最基本的概念开始介绍, 将介绍基础的分析工具, 包括贝尔曼公式和贝尔曼最 优公式, 然后推广到基于模型的和无模型的强化学习算法, 最后推广到基于函数逼近的强化学习方 法。本书强调从数学的角度引入概念、分析问题、分析算法, 并不强调算法的编程实现。本书不要求 读者具备任何关于强化学习的知识背景, 仅要求读者具备一定的概率论和线性代数的知识。如果读者 已经具备强化学习的学习基础, 本书可以帮助读者更深入地理解一些问题并提供新的视角。 本书面向对强化学习感兴趣的本科生、研究生、研究人员和企业或研究所的从业者。 "
本书从零开始介绍,从数学角度循序渐进地揭示强化学习的基本原理。如果你对强化学习感兴趣,却不知道如何入门;如果你对强化学习一直有云里雾里、似懂非懂的感觉,那么相信本书能帮助你拨开迷雾,看清强化学习的本质,知其然,更知其所以然!
Preface This book aims to provide a mathematical but friendly introduction to the fundamental concepts, basic problems, and classic algorithms in reinforcement learning. Some essential features of this book are highlighted as follows. * The book introduces reinforcement learning from a mathematical point of view. Hopefully, readers will not only know the procedure of an algorithm but also understand why the algorithm was designed in the first place and why it works effectively. * The depth of the mathematics is carefully controlled to an adequate level. The mathematics is also presented in a carefully designed manner to ensure that the book is friendly to read. Readers can selectively r...
Contents
Overview of this Book 1
Chapter 1 Basic Concepts 6
1.1 A grid world example 7
1.2 State and action 8
1.3 State transition 9
1.4 Policy 11
1.5 Reward 13
1.6 Trajectories, returns, and episodes 15
1.7 Markov decision processes 18
1.8 Summary 20
1.9 Q&A 20
Chapter 2 State Values and the Bellman Equation 21
2.1 Motivating example 1: Why are returns important? 23
2.2 Motivating example 2: How to calculate returns? 24
2.3 State values 26
2.4 The Bellman equation 27
2.5 Examples for illustrating the Bellman equation 30
2.6 Matrix-vector form of the Bellman equation 33
2.7 Solving state values from the Bellman equation 35
2.7.1 Closed-form solution 35
2.7.... 查看详情