Reinforcement Learning: An Introduction
First Edition (see here
for second edition)
Press, Cambridge, MA, 1998
A Bradford Book
CourseMaterials Html version @Amazon
This introductory textbook on reinforcement learning is targeted toward
engineers and scientists in artificial intelligence, operations
research, neural networks,
and control systems, and we hope it will also be of interest to
psychologists and neuroscientists.
There are also Japanese and Russian translations
Scanned versions are available through MIT CogNet at
many university web sites.