(8)
 
Universal Artificial Intelligence : Sequential Decisions Based on Algorithmic Probability
by Marcus Hutter

Overview -

This book presents sequential decision theory from a novel algorithmic information theory perspective. While the former is suited for active agents in known environments, the latter is suited for passive prediction in unknown environments. The book introduces these two different ideas and removes the limitations by unifying them to one parameter-free theory of an optimal reinforcement learning agent embedded in an unknown environment.  Read more...


 
Hardcover
  • $109.00

Add to Cart + Add to Wishlist

In Stock. Usually ships within 24 hours.

This item is Non-Returnable.
Free Shipping is not available for this item.

Not a member? Join Today!
 
 
New & Used Marketplace 16 copies from $66.15
 
 
 
 

More About Universal Artificial Intelligence by Marcus Hutter
 
 
 
Overview

This book presents sequential decision theory from a novel algorithmic information theory perspective. While the former is suited for active agents in known environments, the latter is suited for passive prediction in unknown environments. The book introduces these two different ideas and removes the limitations by unifying them to one parameter-free theory of an optimal reinforcement learning agent embedded in an unknown environment. Most AI problems can easily be formulated within this theory, reducing the conceptual problems to pure computational ones. Considered problem classes include sequence prediction, strategic games, function minimization, reinforcement and supervised learning. The discussion includes formal definitions of intelligence order relations, the horizon problem and relations to other approaches. One intention of this book is to excite a broader AI audience about abstract algorithmic information theory concepts, and conversely to inform theorists about exciting applications to AI.


This item is Non-Returnable.

 
Details
  • ISBN-13: 9783540221395
  • ISBN-10: 3540221395
  • Publisher: Springer
  • Publish Date: October 2004
  • Page Count: 278

Series: Texts in Theoretical Computer Science

Related Categories

Books > Computers & Internet > Intelligence (AI) & Semantics

 
BAM Customer Reviews

DISCUSSION