Article
files/books/S1591406463

Preview of Biologically Inspired Artificial Intelligence for Computer Games (Book)

Alex J. Champandard on January 20, 2008

A new book recently came out explaining how to apply biologically inspired AI to games. It covers the classics in computational intelligence such as genetic algorithms, neural networks, artificial immune systems and particle swarm optimizations — not forgetting underrated techniques like reinforcement learning, independent component analysis, and radial basis functions.

I found out about the book via the Learning Games blog by Daniel Livingstone, who co-authored the book. As a disclaimer, I was asked to write the foreword for this book over 2 years ago (posted below), but the content has changed significantly since then. It’s great to see this book finally hitting the shelves!

This book’s edition is currently a hardcover, and is available from Amazon.com resellers at round $82 USD, and Amazon.co.uk resellers for around

Discussion 1 Comments

qwerty01 on January 20th, 2008

A little review: The book explain hard topics in a very clear style. The first time I read and "understand" something about neural networks (it's about more then ten years ago), it was thank to Prof. Fyfe's online course material found via a web search. The book preserve the clear explanation and it's easy for a novice to understand ANN, GAs etc. On other hand the part related to examples and pratical applications is lacking of real world examples; It's just about using ANNs, GAs, RL for simple games like "pong". The only real world possible example is about a motocross game where the AI motocross rider is based upon an ANN, but there are little details and no code or pseudo code just an explanation on how the ANN was setup (inputs, outputs etc.). My final vote (1 min/5 max) : 3,5 "Good introduction for AI devs that want to know more about exotics AI applications for games". A little cookie: the foreword is made by our "Lord of AI-bits" Alex.

If you'd like to add a comment or question on this page, simply log-in to the site. You can create an account from the sign-up page if necessary... It takes less than a minute!