Question posted in 
I’ve recently come across Intelligent Agents by reading this book :
link text
I’m interested in finding a good book for beginners, so I can start to implement such a system.
I’ve also tried reading “Multiagent Systems : A modern approach to distributed artificial intelligence” (can’t find it on amazon) but it’s not what I’m looking for.
Thanks for the help :).
3
Answers
There is numerous classical books:
The first two are the easiest, the second one covers more than machine learning. However, there is little “pragmatic” or “engineering” stuff in there. And the math is quite demanding, but so is the whole field. I guess you will do best with O’Reilly’s programming collective intelligence because it has its focus on programming.
The agent view point is simply an abstraction of convenience. There is nothing magical about agents. It is a way of thinking about software processes that may be migrated from one system to another.
So, yes, if you want your agents to be intelligent, then you need to understand AI algorithms.
The book you have linked is actually a collection of invited research papers, which means it is quite an advanced book if you are just starting in Intelligent Systems.
Actually, there are two interpretations of Intelligent Systems:
(a) Artificial Intelligence studied mainly by the Computer Science community. AI deals with machine learning, knowledge representation and reasoning, learning and planning methods. AI is about developing algorithms. The absolute reference to AI is: “Artificial Intelligence, A modern approach“
Although you are referring to this interpretation, in case you are interested, here is the second one:
(b) Intelligent Control Systems studied mainly by Electrical Engineers. It deals with designing intelligent systems that are able to adapt to changes in the environment, able to learn, able to make intelligent decisions, etc. Intelligent systems deals with developing mathematical models of “intelligence” that can be applied to real-world systems, so as to optimize their performance (or some other measure). The tools used are mostly adaptive control, neural networks and optimization methods. There isn’t an easy to follow book on this subject, however some excellent articles are here and here. Also, an excellent reference on Neural Networks is “Neural Networks, A Comprehensive Foundation“