强化学习：一本高清完整版的入门指南

需积分: 10 118 浏览量更新于2024-07-18 收藏 86.08MB PDF 举报

"《强化学习：入门》第二版，由Richard S. Sutton和Andrew G. Barto撰写，属于麻省理工学院出版社的Adaptive Computation and Machine Learning系列书籍，是一本高清完整版的强化学习经典教材。" 《强化学习：入门》第二版是Richard S. Sutton和Andrew G. Barto的经典著作，这本书深入浅出地介绍了强化学习的基本概念、算法和应用，是学习和研究强化学习的重要参考文献。强化学习作为人工智能领域的一个关键分支，通过与环境的交互，使智能体学会做出最优决策，以最大化长期奖励。在本书中，作者详细阐述了强化学习的基础理论，包括马尔可夫决策过程（Markov Decision Processes, MDPs）、动态规划（Dynamic Programming）、价值函数、策略搜索以及Q学习等核心概念。这些理论是理解强化学习算法如Q-learning、SARSA和Deep Q-Network (DQN)等的基础。第二版对第一版进行了更新和扩展，可能包含了新的研究成果、改进的算法以及更多实际应用案例。比如，随着深度学习的发展，书中可能涵盖了如何结合神经网络进行深度强化学习，以及在游戏控制、机器人、自然语言处理和推荐系统等领域中的应用。此外，书中的封面设计灵感来源于一个由强化学习系统控制的模拟自行车的轨迹，生动展示了强化学习在动态控制问题中的潜力。书中的例子和练习旨在帮助读者理解和实践强化学习的方法。本书适合计算机科学、人工智能和机器学习专业的学生，以及对该领域感兴趣的从业者阅读。通过学习，读者将能够掌握强化学习的基本原理，具备设计和实现强化学习算法的能力，从而解决实际问题。《强化学习：入门》第二版不仅是一本理论详尽的教材，也是实践指导的宝典，对于希望深入理解和应用强化学习的人士来说，是不可或缺的参考资料。

xvi Preface to the Second Edition

deserve our deepest gratitude for this edition as well, which wou ld not exist were it not

for their contributions to editi on number one. To that long list we must ad d many others

who contributed speciﬁcally to the second edi ti on . Our students over the many years that

we have taught this material contributed in countless ways: exposi ng errors, o↵ering ﬁxes,

and—not the least—being confused in places where we could have explained things better.

We especially thank Martha Steenstrup for reading and providing detailed comments

throughout. The chapters on psychology and neuroscience could not have been written

without the help of many experts in those ﬁelds. We thank John Moore for his patient

tutoring over many many years on animal learning exper im ents, the ory, and neuroscience,

and for his careful reading of multiple drafts of Chapters 14 and 15. We also thank Matt

Botvinick, Nathaniel Daw, Peter Dayan, and Yael Niv for their penetrating comments on

drafts of these chapter, their essential guidance through the massive literature, and their

interception of many of our errors in early drafts. Of course, the remaining errors in these

chapters—and there must still be some—are totally our own. We t han k Phil Thomas for

helping us make these chapters accessible to non-psychologists and non-neuroscientists,

and we thank Peter Sterling for helping us improve the exposition. We ar e grateful to Jim

Houk for introducing us to the subject of information processing in the basal ganglia and

for alerting us to other relevant aspects of neuroscie nc e. Jos´e Mart´ınez, Terry Sejnowski,

David Silver, Gerry Te s aur o, Georgios Theocharous, and Phil Thomas generously helped

us understand details of their reinforcement learning applications for incl u si on in the

case-studies chapter, and they provided helpful comments on drafts of these sections.

Special thanks are owed to David Silver for helpi ng us better understand Monte Carlo

Tree Search and the DeepMind Go-playing programs. We thank George Konidaris for his

help with the section on the Fourier basis. Emilio Cartoni, Thomas Cederborg, Stefan

Dernbach, Clemens Rosenb aum , Patrick Taylor, Thomas Colin, and Pierre-Luc Bacon

helped us in a number important ways for which we are most grateful .

Sutton wou l d also like to thank the members of the Reinforcement Le arn i ng and

Artiﬁcial Intellige nc e laboratory at the University of Alberta for contributions to the

second edition . He owes a particular debt to Rupam Mahmood for essential contributions

to the treatment of o↵-policy Monte Carlo methods in Chapter 5, to Hamid Maei for

helping develop the perspective on o↵-policy learning presented in Chapter 11, to Eric

Graves for conducting t h e experiments in Chapter 13, to Shangtong Zhang for replicating

and thus verifying almost all the experimental results, to Kr is De Asis for improving

the new technical content of Chapters 7 and 12, and to Harm van Seijen for insights

that led to the separation of n- st ep me t hods from eligibi l ity traces and (along with Hado

van Hasselt) for the ideas involving exact equivalence of forward and backward views of

eligibility traces presented in Chapter 12. Sutton also gratefully acknowledges the support

and freedom he was granted by the Government of Alberta and the National Science and

Engineering Research Council of Canada throughout the period during which t h e second

edition was conceived and written. In particular, he would like to thank Randy Goebel

for creating a supportive and far-sighted environment f or res ear ch in Alberta. He would

also like to thank DeepMind their support in the last six months of writing the book.

Finally, we owe t han k s to t he many careful readers of drafts of t he second edition that

we post e d on the internet. They found many errors that we had missed and alerted us to

potent i al points of confusion.

Preface to the First Edition

We ﬁrst came to focus on what is now known as reinforcement learning in late 1979. We

were both at the University of Massachusetts, working on one of the earliest projects to

revive the idea that networks of neuronlike adaptive elements might prove to be a promising

approach to artiﬁcial adaptive intelligence. The project explored the “heterostatic theor y

of adaptive s ystems” developed by A. Harry Klopf. Harr y’ s work was a rich source of

ideas, and we were permitted to explore them critically and compare them with t h e long

history of prior work in adaptive systems. Our task became one of teasing the ideas apart

and understanding their relationships and relative importance. This continues today,

but in 1979 we came to realize that perhaps the simplest of the ideas, which had long

been taken for granted, had received surprisingly little attention from a computational

perspec t ive. This was simply the idea of a learning system that wants something, that

adapts its behavior in order to maximize a special signal from its environment. This

was the idea of a “hedonistic” learning system, or, as we would say n ow, the idea of

reinforcement learning.

Like others, we had a sense that reinforcement learning had been thoroughly explored

in the early days of cybernetics and artiﬁcial intelligence. On closer inspection , though,

we found that it had been explored only slightly. While rei nf orc em ent learni n g had c l e arl y

motivated some of the earli est computational studies of learning, most of these researchers

had gone on to other things, such as pattern classiﬁcation, supervised learning, and

adaptive control, or they had abandoned the study of learning altogether. As a result, t he

special issues involved in learning how to get something from the environment received

relatively little attention. In retrospec t, focusing on this idea was the critical step that

set this branch of research in motion. Little progress could be made in the computational

study of reinforcement learning until it was recognized that such a fundamental idea had

not yet been thoroughly explored.

The ﬁeld has come a long way since t h en , evolving and maturing in several directions.

Reinforcement learning has gradually become one of the most act i ve research areas in ma-

chine l ear nin g, artiﬁcial intelligence, and neu r al network research. The ﬁeld has developed

strong mathematical foundations and impressive applications. The computational study

of reinforcement learning is now a lar ge ﬁeld, with hundreds of acti ve researchers around

the world in diverse disciplines such as psychology, control theory, artiﬁcial intelligence,

and neuroscience. Particularly important h ave been the contributions establishing and

developing the relationships to the theory of optimal control and dynamic programming.

xvii

xviii Preface to the First Edition

The overall problem of learning from interaction to achieve goals is still far from being

solved, but our understanding of it has improved signiﬁcantly. We can n ow place compo-

nent ideas, such as temporal-di↵erence learning, dynamic programming, and function

approximation, within a coherent perspective wi t h respect to the overall problem.

Our goal in writing this book was to provide a clear an d simple account of the key

ideas and algori t h ms of reinforcement learning. We wanted our treatment to be accessibl e

to readers in all of the related discipli ne s, but we could not cover al l of these pe rs pectives

in detail. For the most part, our treatment t akes the point of view of artiﬁcial intelligence

and engineering. Coverage of connections to other ﬁelds we leave to others or to another

time. We also chose not to produce a rigorous formal treatment of reinf or ce ment learning.

We did not reach for the highest possible level of mathematical abstraction and did not

rely on a theorem–proof format. We tried to choose a level of mathematical detail that

points the mathematically inclined in the right directions without distracting from the

simplicity and potential generality of the underlying ideas.

...

In some sense we have been working toward this book for thirty years, and we have lots

of people t o thank. First, we thank those who have personally helped us develop the overall

view presented in this book: Harry Klopf, for helping us recognize that reinforcement

learning needed to be revived; Chris Watkins, Dimitri Bertsekas, J oh n Tsitsiklis, and

Paul Werbos, for helping us see the value of the relationships to dynamic programming;

John Moore and Jim Kehoe, for insights and inspirations from animal learning theory;

Oliver Selfridge, for emphasizing the breadth and importance of adaptation; and, more

generally, our coll eagu es and stu de nts who have contributed in countless ways: Ron

Williams, Charles Anderson, Satinder Singh, Sridhar Mahadevan, Steve Bradtke, Bob

Crites, Peter Dayan, and Leemon Baird. Our view of reinforcement learning has been

signiﬁcantly enriched by discussions with Paul Cohen, Paul Utgo↵, Martha Steenstrup,

Gerry Tesauro, Mike Jordan, Leslie Kaelbling, Andrew Moore, Chris Atkeson, Tom

Mitchell, Nils Nilsson, Stuart Russell, Tom D ie t t er ich, Tom Dean, and Bob Narendra.

We thank Michael Littman, Gerry Tesauro, Bob Cr i te s, S at in d er Si n gh, an d Wei Zh ang

for provid i ng speciﬁcs of Sections 4.7, 15.1, 15.4, 15.4, and 15.6 respectively. We thank

the Air Force Oﬃce of Scientiﬁc Resear ch, the National Science Foundation, and GTE

Laboratories for their long and farsighted sup port.

We also wish to than k the many people who have read drafts of this book and

provided valuable comment s, including Tom Kalt, John Tsitsiklis, Pawel Cichosz, Olle

G¨allmo, Chuck Anderson, Stuart Russell, Ben Van Roy, Paul Steenstrup , Paul Cohen ,

Sridhar Mahadevan, Jette Ran dlov, Brian Sheppard, Thomas O’Connell, Richard Coggins,

Cristina Versino, John H. Hiett, Andreas Badelt, Jay Ponte, Joe Beck, Justus Piater,

Martha Steenstrup, Satinder Singh, Tommi Jaakkola, Dimitri Bertsekas, Torbj ¨orn Ekman,

Christina Bj¨orkman, Jakob Carlstr¨om, and Olle Palmgren. Finally, we t hank Gwyn

Mitchell for helping in many ways, and Harry Stanton and Bob Prior for being our

champions at MIT Press.

剩余547页未读，继续阅读

srh2006

粉丝: 0
资源: 3

强化学习：一本高清完整版的入门指南

增强学习导论（Reinforcement Learning An Introduction_Sutton）

Reinforcement Learning-An Introduction by Sutton R S，Barto A G

Reinforcement Learning: An Introduction 2nd solutions （第二版 答案）

Reinforcement Learning an Introduction 第二版有正事封面版

Reinforcement Learning: An Introduction 第二版

Reinforcement Learning - An Introduction 第二版201705

Reinforcement Learning An Introduction (第二版 Draft)

强化学习导论 第二版 英文版 2017最新版 Reinforcement Learning An Introduction

Reinforcement_learning_An_introduction 第二版

book-Reinforcement Learning An Introduction2018最新版.pdf

最新资源

Reinforcement Learning: An Introduction 2nd solutions （第二版答案）

强化学习导论第二版英文版 2017最新版 Reinforcement Learning An Introduction