Universal Artificial Intelligence

Sequential Decisions Based on Algorithmic Probability

  • Marcus Hutter

Table of contents

  1. Front Matter
    Pages i-xx
  2. Marcus Hutter
    Pages 1-27
  3. Marcus Hutter
    Pages 29-63
  4. Marcus Hutter
    Pages 65-124
  5. Marcus Hutter
    Pages 125-140
  6. Marcus Hutter
    Pages 141-183
  7. Marcus Hutter
    Pages 185-208
  8. Marcus Hutter
    Pages 209-229
  9. Marcus Hutter
    Pages 231-249
  10. Back Matter
    Pages 251-280

About this book

Introduction

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.

Keywords

agents algorithmic information theory algorithms artificial intelligence decision theory information information theory intelligence learning reinforcement learning uncertainty

Authors and affiliations

  • Marcus Hutter
    • 1
  1. 1.Istituto Dalle Molle di Studi sull’Intelligenza Artificiale (IDSIA)Manno-LuganoSwitzerland

Bibliographic information

  • DOI https://doi.org/10.1007/b138233
  • Copyright Information Springer-Verlag Berlin Heidelberg 2005
  • Publisher Name Springer, Berlin, Heidelberg
  • eBook Packages Computer Science
  • Print ISBN 978-3-540-22139-5
  • Online ISBN 978-3-540-26877-2
  • Series Print ISSN 1862-4499
  • About this book