Stock photo: cover may vary
Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability Hardback - 2004 - 2005th Edition
by Hutter, Marcus
- Used
- Hardback
A$117.80
A$26.89
Delivery to USA
Standard delivery: 7 to 20 days
More delivery options
Standard delivery: 7 to 20 days
Ships from Anybook.com (Lincolnshire, United Kingdom)
Details
- Title Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability
- Author Hutter, Marcus
- Binding Hardback
- Edition number 2005th
- Edition 2005
- Pages 278
- Volumes 1
- Language ENG
- Publisher Springer, Secaucus, New Jersey, U.S.A.
- Publication date 2004
- Illustrated Yes
- Features Bibliography, Illustrated, Index, Table of Contents
- Bookseller's Inventory # 8604589
- ISBN 9783540221395 / 3540221395
- Weight 1.43 lbs (0.65 kg)
- Dimensions 9.46 x 6.54 x 0.8 in (24.03 x 16.61 x 2.03 cm)
- Category Computers - General Information
- Library of Congress Catalogue Number 2004112980
- Dewey Decimal Code 006.3
About Anybook.com Lincolnshire, United Kingdom
Biblio member since 2004
Established in 1998 Anybook.com. has sold millions of scholastic books to university libraries, academics, students and reflective bibliophiles throughout the world. As the majority of our books are ex-library they are well bound, in good, clean condition and ideally suited for study and research. Our books cover a huge range of academic disciplines from Mathematics, Science and Philosophy to Art and Literature as well as many works in other European languages.
Based in central Lincoln, Anybook.com. sells exclusively online. We specialise in academic works. All our books are in good condition or better, unless otherwise described. All the books we have on sale are to hand in our warehouses in Lincoln. Photographs and additional information on request. Books out within 1 working day. We use reputable couriers at greatly discounted postage rates. As well as Visa and Mastercard, we also accept Switch, Discover and Solo. We also accept Paypal (www.paypal.com) payments. Other methods of payment are possible but please email us for details. Remember if you are unsatisfied in any way with any purchase, we will give you a complete and unconditional refund. E-mail us if you have any questions about the service we offer. Please be aware our prices and shipping costs do not include local import taxes which may need to be paid by the customer upon receipt.
Reader reviews for Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability
Write a review for this book
Important Terms and Guidelines
- Please focus on the book’s content and context. Also, add any personal comments as to how you enjoyed the book. Substantiate your likes and dislikes. You may make comparisons to other books.
- Reviews must be at least 140 characters in length.
- Please do not reveal critical plot elements.
- This is not a help line. Contact customer support if you need help.
Your review must not include:
- Obscenities, discriminatory language, or other insulting language not suitable for public domain
- Advertisements, “spam” content, or references to other products, offers or websites.
- Email addresses, URLs, phone numbers, physical addresses or other contact information.
- Overly critical comments about other reviews or reviewers
- Time-sensitive material (i.e. promotional tours, seminars, lectures, etc.)
- Availability, price, or alternative ordering/shipping information
From the publisher
First line
HASH(0x11135460)
From the rear cover
Decision Theory = Probability + Utility Theory
+ +
Universal Induction = Ockham + Bayes + Turing
= =
A Unified View of Artificial Intelligence
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 well-known but very different ideas and removes the limitations by unifying them to one parameter-free theory of an optimal reinforcement learning agent embedded in an arbitrary unknown environment. Most if not all AI problems can easily be formulated within this theory, which reduces 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 to AI. 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.
