Following the accolades in the reviews and having a keen interest in AI (as a physician and computer scientist) - I have dived into this book. It took me more than half a year of stubbornly trying to read and understand it. What a disappointment...
On one hand, the math is inaccessible, least you have a major in computer sciences / statistics, math - or all of the above. It seems some, if not all of the math "proofs" are unnecessary for the matter at hand. Unless there are some sinister motives behind these superfluous math complications - such as providing professors with ammunition for students testing. But why should someone interested in AI - get bogged down in this? Is it really what the authors had in mind?
On the other hand there are not enough examples to follow and the examples that are there - are inconsistent and insufficient (for example: the `wumpus' world that is used in the logic chapters, actually succeeds to stir an interest in the reader and then ....it is not followed up in the subsequent chapters such as the one on Bayesian networks)...
Some easy to grasp principles (such as basic propositional logic) are repeated ad nauseam while some difficult subjects (such as MCMC) are left as puzzling axioms, for us to decipher on our own.

I summarize my disappointment asking myself what I got from this effort that I have invested into this book, absorption and digestion wise, professionally speaking:
1. Did this book help me better understand the depth and breadth of the AI domain? - No.
2. Am I able to develop, even conceptually a plan for an AI application / "intelligent agent"? Absolutely not.
3. Did the book clarify for me the fields of logic, machine learning, reasoning, uncertainty, probability and so on? - No. I am as confused now as I was before embarking on this study project, maybe even more so.
4. Am I a smarter person, able to read now the multitude of scientific articles out there on the AI subject - after finishing this book? - No.

The only reason I gave it 2 stars instead of the single one it deserves - is because of the historical and bibliographical summaries the authors have nicely detailed at the end of each chapter. I've seen other books recommended in these reviews - and I intend to look into them shortly. CAVEAT EMPTOR (buyer beware) !

Form your own opinion on this book, don't let the gushing over this book force you into questioning your instincts

I thought I liked this book at first, but I had confused interest in AI with regard for this book.

Sure this was ground breaking. But, currently, it is bloated, full of wordy, unclear descriptions. I particularly dislike the coverage in: ch. 7, 8, 9 (logics + reasoning). ch. 13, 14 (prob, belief nets). Make the search chapters shorter, fewer. We get the idea, no need to spend so much time on it. Make the logic chapters shorter, dig deeper into those subjects if you want to use that much of the readers time. Scrap chapter 13 or write it over again (refer reader to Pearl's or others coverage of probability). It is partially to elementary, stating obvious rules with very simple usages. The rest of it jumps around, with unclear explanations. Chapter 14, skims past ideas, not enough time spent explaining ideas.

I particularly like the detailed references at the end of each chapter.

After glancing at Winston, Nilsson, and Poole books, I am leaning towards Poole, especially since I am more interested in the knowledge rep and reasoning than other areas.

Pros: Well organized, Description is clear and complete, good for beginners.
Cons: Examples chosen are not the best, author's attempts at humor are quite lame in most cases.

I am half way through and I like it so far. Frankly I am puzzled by other reviewers complaining about "lack of real code examples", they clearly have not read the book carefully: it comes with tons of sample code (online) written in different languages, publishers/authors simply did not want to waste the precious real estate. The book is nearly a thousand pages already.

Otherwise this is a great CS book. Yes there is some math in it, but don't be scared - there is an appendix with all necessary mathematical background you'll need (and you don't need much). I was surprised to see so much historical references in this book, it teaches you not just about most major branches of AI, but also about how they started and where originated from in a "problem -> solution" form. For instance when they talk about genetic algorithms they actually go ahead and write a comprehensive comparison of analogies between biological evolution, genes and their computer-generated counterparts referencing the original work of Darwin and others.

If you're into AI, applied mathematics or computer science, I have no doubt you'll enjoy this book: it's not too focused on something specific (and something you'd need a PhD to understand) while not too shallow and covers fairly wide spectrum of AI problems, including (!) ethical and philosophical issues like "what happens if we succeed?"

Highly recommended.

An author of this book is said to have commented that its writing has made him a millionaire. It is used in over 1000 universities for a simple reason, it is good. The book uses the concept of an agent to unify the formerly fragmented field of AI and to link together concepts as diverse as logic programming and ethics. It is very easy to read and touches every area of modern research interest I can think of. The problems have a nice variety of difficulties (although there are no worked-out solutions in the book) and provide a mix between theory and practice, introducing the careful student to concepts and papers not developed in the main text of the chapter. The bibliography is well laid-out and provides useful depth (one of my current research interests was sparked by reading one of the referenced papers in the 2nd chapter).

My only complaint so far (not having finished the entire book) is that some of the definitions in chapter 17's whirlwind introduction to game theory were a little vague. But, a quick look at some other sources clarified things immensely.

It is rare to find a textbook as interesting and clear as this one. If a professor is requiring that you read it, consider yourself fortunate. If you are thinking of reading it yourself, you also are blessed. Look forward to many pleasant evenings.

This book is very worthwhile if you are looking into AI with the purpose of understanding the various techniques, etc. It gives a really good background, and I find it useful. The only changes I would have made (for me, not everyone else) would be to include a few short chapters on second order logic, and the basic mathematics and math terms used in the book. It assumes more knowlege in math than I have. It would also be nice if it had a "recommended reading" page, listing those texts that would be useful for an AI beginner to review in order to understand the math and logic referred to. (My degree was in 79, and I only had a very basic calculus course...not too deep...I can diffentiate, but that is all).

It would just be nice if they could list reference books for people who are math nieve.

This book was very thorough in many facets of Artificial Intelligence. It was a tremendous help in the class I took and will be a great reference for future years.

Useful book which at first explains in great detail the history, foundations for AI and the different approaches AI takes on. Your course will probably not use all the material in the book but still makes for interesting reading. Would recommend if you can pick up a copy cheap.

Lack of coded examples. Language is muddy in spots. Annoyingly redundant at various points. Obviously two authors. Terms/nomenclature are not always defined and SHOULD always be defined before being used. The pseudocode is a mish mash - takes some getting used to. GUYS! for heavens sake supplement with REAL programming language examples - PREFERABLY C++. Not a single WORKING rational agent in the text. So, you know what you are doing? PROVE IT! In general good information - definitely a two semester text.

the book was in excellent condition.it arrived on time.i am quite happy with the service provided by amazon.

hrishi

This book is an excellent book for those who want to get acquainted with Artificial Intelligence. It covers a wide range of topics and includes algorithms for many of the topics.

I suggest this book for anyone interested in learning to design and implement AI in their academic and work projects.

Tends to oversimplify example algorithms, other than that it's a great book.

This book is excellent for a novice in AI. Chapter by chapter - though chapters vary in thoroughness and detail - the book illustrates AI techniques by family by accessibly presenting the problems that motivate the techniques, and the logic applied to implement them (pseudo-code).

Arguably the book is written from the easier towards the harder methods. It's a good treatment on search strategy and basic logic, but notably somewhat lacking in pattern recognition, unbound optimization, and some machine learning topics, which is understandable considering how extensive the subjects are.

As a starting point towards learning about AI techniques, or as a course text-book the Russel and Norvig (this) book is an excellent resource. The book will set up a student with a mindset towards identifying search, optimization and reasoning problems that lend themselves towards AI solutions, and how to pick the appropriate technique to solve them.

Note that the book presents all of these techniques through a framework of thought around intelligent agents (which can be somewhat confusing considering you will later mostly hear the keyword 'agent' in AI techniques that apply social intelligence, or solve problems via interactions between somewhat independent intelligent constructs).

Follow up with Duda's "Pattern Classification", and Mitchell's "An Introduction to Genetic Algorithms (Complex Adaptive Systems)" for a more in depth treatment on Machine Learning problems and solutions and Genetic Algorithms. Maybe also some reading on swarm intelligence, and you'll have good referential knowledge and a decent tool-set of AI reasoning and problem solving skills.

The authors furnish a voluminous and up to date survey of AI. Covering the gamut of ideas and computational techniques common to the field. Unsurprisingly, there is plenty of discussion about formal logic methods and how to develop inferences in a manner doable by a computer. This is expanded into describing ontologies and how to find knowledge in a learning process. All of these are hard topics that try to attack a fundamentally difficult problem.

Other ideas explored include neural networks. Very different from a formal deductive stance. The learning here is done in training sessions that can be very extensive. Interesting that the book includes prominent discussion of neural networks. I recall that in the 80s, this was considered by some AI people not to be a valid AI approach. But the authors have taken a more pragmatic and inclusive view.

The choice of "intelligent agent" in the subtitle is interesting. It can be seen as positioning the AI methods for application to such agents. These have been and are widely mooted as perhaps one promising future direction for deployment on the Web.

This book was used in both my undergraduate and graduate courses in artificial intelligence. It is a very readable book, and an enormously useful reference. I believe they at least do a cursory overview of the most critical concepts in AI, and if they don't, there are usually great references at the end of the chapter.

That is actually my favorite features of this book. At the end of each chapter, Norvig and Russell will give something like an annotated bibliography, but with much more depth.

This is the book to buy if you are interested in any topic dealing with AI. If there is a topic in AI that you are interested in, then this book with have some information about it.

The material clear and has the depth required for detailed study. I am still reading but I have enjoyed it thoroughly uptil now.

Great book. Very detailed introduction to concepts in AI.

Was cheaper than used copies at my school's bookstore, too!

I had to buy this book for my study, but I don't really like it. There are too many examples, which takes a lot of time to read.

This is a great book for anyone who wants to get serious on AI algorithms - it has a vast coverage of most well-known algorithms and techniques, not only presenting them, but also analyzing their performance and possible uses.

Amazing effort in compiling historical roots, facts, concepts, applications from a relatively recent formal discipline (about 50 years old) and always in evolution, very inspiring piece of work I must add. This book goes from the very AI concepts towards the depth AI modeling methods analysis with clear and easy explanations beyond any other book I have ever read. A must for every AI enthusiast, reader, teacher and student, highly recommended if you want to contribute to this science even by yourself.

We used this textbook for the introductory and advanced AI classes at my university, and I was very impressed with it. The book's coverage is comprehensive, but more importantly the explanation of concepts is both clear and interesting. The authors clearly have a mastery of the material, but at the same time they seem to understand how to present it in a clear and understandable fashion. The quality of the writing and editing is high -- I noticed a single trivial typo while reading a few hundred pages of the book fairly intensively. I would guess the authors' really enjoyed writing the book; certainly from the result it seems that way.

Overall, this is among the best textbooks I've ever used, and it's certainly something I intend to refer back to -- and probably reread -- in the future. Highly recommended.

Always good to see yet another book on AI. Not a bad addition to the library. Not well written

the book is the most cohesively extensive I have ever read regarding the subject. Although AI is a very broad and evolving discipline, the authors have successfully lay down the foundation of the science and elucidate the important and promising aspects of AI.

I didn't think that the first edition of this book was as bad as some of the reviewers said, but the second edition is definitely a vast improvement. It's not just some obligatory 2nd edition that some authors release to say that they are staying actively published. The first edition was somewhat confusing in its explanations and the exercises were really blurry on what was being asked. All of that has now been resolved.
The book is a comprehensive and insightful introduction to artificial intelligence with an academic tone. It provides a unified view of the field organized around the rational decision making paradigm, which focuses on the selection of the "best" solution to a problem. The book's overall theme is that the purpose of AI is to solve problems via intelligent agents, and then goes about specifying the features such an agent or agents should have. Pseudocode is provided for all of the major AI algorithms. Being about the broadest book in terms of coverage of AI, you should therefore not expect it to be the deepest in coverage. However, each topic is covered to the extent that the reader should understand its essence. Sections one through six are absolutely wonderful, and comprise the "meat" of AI. Section seven is rather weak since it tries to cover both robotics and text processing in their own individual chapters, and entire books have a hard time covering this material. Section eight is different from the others, since it talks about the philosophy and future of AI.
Another plus for this book is that there is a great deal of extra material that deals with standard AI curriculum. For example, the chapters on logic not only include the typical introduction to propositional and first order logic together with the usual inference procedures, they also give many useful hints how to use first order logic to actually represent aspects of the real world such as measures, time, actions, mental objects, etc. These chapters also contain much information about how to implement efficient logical reasoners.
Finally, this second edition has an excellent website that can be found by going through the publisher's webpage for the book. This website contains four sample chapters, pseudocode, and actual code in Java, Python, and LISP.
I notice that Amazon shows the table of contents from the first edition, so I am showing what the actual table of contents is for the second edition for the purpose of completeness. Note that the book has been significantly reorganized.
I. ARTIFICIAL INTELLIGENCE.
1. Introduction.
2. Intelligent Agents.
II. PROBLEM-SOLVING.
3. Solving Problems by Searching.
4. Informed Search and Exploration.
5. Constraint Satisfaction Problems.
6. Adversarial Search.
III. KNOWLEDGE AND REASONING.
7. Logical Agents.
8. First-Order Logic.
9. Inference in First-Order Logic.
10. Knowledge Representation.
IV. PLANNING.
11. Planning.
12. Planning and Acting in the Real World.
V. UNCERTAIN KNOWLEDGE AND REASONING.
13. Uncertainty.
14. Probabilistic Reasoning Systems.
15. Probabilistic Reasoning Over Time.
16. Making Simple Decisions.
17. Making Complex Decisions.
VI. LEARNING.
18. Learning from Observations.
19. Knowledge in Learning.
20. Statistical Learning Methods.
21. Reinforcement Learning.
VII. COMMUNICATING, PERCEIVING, AND ACTING.
22. Agents that Communicate.
23. Text Processing in the Large.
24. Perception.
25. Robotics.
VIII. CONCLUSIONS.
26. Philosophical Foundations.
27. AI: Present and Future.

This book is a great book in AI. It covers broad AI topics. It is easy to understand.

Artificial Intelligence: A Modern Approach (2nd Edition)
by Stuart J. Russell was a required reading for my studies (algorithms).. It is an absolutely wonderful text, covering nearly all facets of AI from robotics to building a knowledge base. While most of my other college texts were returned to the book store once the class was finished- this one did not. The wealth of information within will serve valuable time and time again.
I also had to read Human Interface by Jason Giacchino this semester. A fiction novel that will also avoid going back to the campus book store- highly recommended.

This is the text that I learned AI from and has served me well over the years.

I am taking an artificial intelligence class and am very satisfied with this book so far. The material isn't presented in an overly complex fashion yet you are not left with a subset of the information. While it may not have the lasting power of say the the Redbook(for OpenGL), it does do the trick and from what I have seen this is the best option out there.

I also have to give props to Amazon. When making my order there were some problems with shipping and it got sent overnight rather than super savings. I notified amazon and was refunded the shipping. Great service. Great book. What can I say.

I read this along with the white papers by Stuart Russell and can say that The Artificial Intelligence Laboratory at the Vrije Universiteit Brussel, or short VUB AI-Lab, was founded in 1983 by Luc Steels and is part of the Computer Science Department,and compares well after reading this book on how to apply both to each other.

Over the years, more than hundred researchers have worked at the laboratory. They have built a large number of artificial systems to investigate aspects of intelligence: Aaron Kalvani worked on the knowledge systems, autonomous robots, machine learning systems, natural language processing components, design and implementation tools. This was then applied using Stuarts Theories which advanced the AI Science on to stage two. Facinating reading.

Realmente, estou muito satisfeita com a compra que fiz e com a forma com a Amazon tratou meu pedido.
Foi recebido no prazo estipulado. Sempre estarei comprando com a Amazon.com

I think the book is good overall, it could be more focused in some places and have better examples for the students.

My major point with writing this review though is to counter false claim from the reviewer who wrote the "Survey type of book, shallow but good for reference", the book does cover Simulated Annealing, see page 116 in the International Edition for instance.

This is currently the best general purpose book on AI (the field). It is by no means the best book on any individual topic though... but I guess that wasn't the point of the book to begin with.

I'm not particularly happy with this book though. I think it's the language, or the examples, or something, but often it's just not `clear'---not as intuitive as I'd like. Many teachers seem to use it in a `general purpose course on AI' though (not anything particularly detailed, so it's `ok'---there are worse books on the subjects).

In short: as a general purpose AI book on everything, it does its job, but don't expect it to be anything other than a glorified field overview.

the book enters all the aspects of AI today and tomorow.

Until recently, my Algorithms book was my favorite text book ever. However, AI: A Modern Approach has supplanted it. This book is the most thoughtfully designed, easily understandable, clear text I've ever used in over 28 years of attending schools. I really knew nothing about AI when I took my first grad class in AI, but this book, along with a pretty great instructor, has been a wonderful resource, more than any other book I've used. I have not need to google for more information or speak to the professor. The answers are here--clear and concrete.

Have no fear and trust this book!