Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability / Edition 1

Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability / Edition 1

by Marcus Hutter
     
 

ISBN-10: 3540221395

ISBN-13: 9783540221395

Pub. Date: 11/29/2004

Publisher: Springer Berlin Heidelberg

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

…  See more details below

Overview

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.

Read More

Product Details

ISBN-13:
9783540221395
Publisher:
Springer Berlin Heidelberg
Publication date:
11/29/2004
Series:
Texts in Theoretical Computer Science. An EATCS Series
Edition description:
2005
Pages:
278
Product dimensions:
0.69(w) x 9.21(h) x 6.14(d)

Table of Contents

1. A Short Tour Through the Book; 2. Simplicity and Uncertainty; 3. Universal Sequence Prediction; 4. Agents in Known Probabilistic Environments; 5. The Universal Algorithmic Agent AIXI; 6. Important Environmental Classes; 7. Computational Aspects; 8. Discussion; Bibliography; Index

Customer Reviews

Average Review:

Write a Review

and post it to your social network

     

Most Helpful Customer Reviews

See all customer reviews >