Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability

Front Cover
Springer, 2005 - Computers - 278 pages
2 Reviews

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.

  

What people are saying - Write a review

We haven't found any reviews in the usual places.

Related books

Contents

A Short Tour Through the Book
1
Simplicity Uncertainty
29
2 Prefix coding of natural numbers and strings
34
14 Kolmogorovs axioms of probability theory
42
25 Posterior convergence of M to i
48
31 MartinL6f random sequences
54
Universal Sequence Prediction
65
8 Convergence of random sequences
71
1 The agent model
126
The Universal Algorithmic Agent AIXI
141
12 We expect AIXI to be universally optimal
146
30 Discounted AIp model and value
159
Important Environmental Classes
185
Computational Aspects
209
1 The fastest algorithm
211
8 Effective intelligence order relation
226

36 Error bound
83
59 Instantaneous loss bound
91
64 Lower error bound
97
65 Pareto optimality
99
Agents in Known Probabilistic Environments
125
Discussion
231
Bibliography
251
Index
265
Copyright

Common terms and phrases

References to this book

All Book Search results »

References from web pages

Universal Artificial Intelligence
@Book{Hutter:04uaibook, author = "Marcus Hutter", title = "Universal Artificial Intelligence: Sequential Decisions based on Algorithmic Probability", ...
www.hutter1.net/ ai/ uaibook.htm

A Theory of Universal Artificial Intelligence based on Algorithmic ...
Decision theory formally solves the problem of rational agents in uncertain worlds if the true environmental prior probability distribution is known
citeseer.ist.psu.edu/ hutter00theory.html

[cs/0004001] A Theory of Universal Artificial Intelligence based ...
arxiv.org > cs > arxiv:cs/0004001. Search for. (Help | Advanced search). All papers, Titles, Authors, Abstracts, Full text, Help pages. Full-text links: ...
arxiv.org/ abs/ cs/ 0004001

citeulike: A Theory of Universal Artificial Intelligence based on ...
Groups. Search groups. citeulike is a free online bibliography manager. Register and you can start organising your references online. ...
www.citeulike.org/ user/ yish/ article/ 462159

A Universal Measure of Intelligence for Artificial Agents
Universal Artificial Intelligence: Sequential Decisions based on Algorithmic Probability. Springer, Berlin, 2004. 300 pages, http://www.idsia.ch/ ...
www.idsia.ch/ idsiareport/ IDSIA-04-05.pdf

Intelligent machines that learn unaided
May 1997: world chess champion Garry Kasparov is. defeated by Deep Blue, ibm's supercomputer. At the end. of the game, Kasparov admitted to feeling as if ...
www.ticinoricerca.ch/ catprog/ attachment/ documentazioni/ Ristampa_PM9_ENG.pdf

Universal Artificial Intelligence Seque | Marcus Hutter en venta ...
Title: Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability. Author: Marcus Hutter. Publisher: Springer-Verlag Berlin ...
cgi.ebay.es/ Universal-Artificial-Intelligence-Seque-Marcus-Hutter_W0QQitemZ270225746732QQihZ017QQcategoryZ1107QQcmdZ...

Marcus Hutter - Wikipedia, the free encyclopedia
Universal Artificial Intelligence: Sequential Decisions Based On Algorithmic Probability ISBN 3-540-22139-5. On Generalized Computable Universal Priors and ...
en.wikipedia.org/ wiki/ Marcus_Hutter

Universal Artificial Intelligence - Boek - BESLIST.nl
Bekijk en vergelijk informatie, beoordelingen, vragen & antwoorden en de beste winkels voor 'Universal Artificial Intelligence' op BESLIST.nl ▪ Boeken ...
boeken_engels.beslist.nl/ boeken_engels/ d0000761068/ Universal_Artificial_Intelligence.html

Towards a Universal Theory of Artificial Intelligence based on ...
Marcus Hutter. - 1 -. Universal Artificial Intelligence. Towards a Universal Theory of Artificial. Intelligence based on Algorithmic Probability ...
www.hutter1.net/ ai/ skcunai.pdf

About the author (2005)

Marcus Hutter received his masters in computer sciences in 1992 at the Technical University in Munich, Germany. After his PhD in theoretical particle physics he developed algorithms in a medical software company for 5 years. For four years he has been working as a researcher at the AI institute IDSIA in Lugano, Switzerland. His current interests are centered around reinforcement learning, algorithmic information theory and statistics, universal induction schemes, adaptive control theory, and related areas.

IDSIA (Istituto Dalle Molle di Studi sull'Intelligenza Artificiale) is a non-profit oriented research institute for artificial intelligence, affiliated with both the University of Lugano and SUPSI. It focusses on machine learning (artificial neural networks, reinforcement learning), optimal universal artificial intelligence and optimal rational agents, operations research, complexity theory, and robotics. In Business Week's "X-Lab Survey" IDSIA was ranked in fourth place in the category "Computer Science - Biologically Inspired", after much larger institutions. IDSIA also ranked in the top 10 of the broader category "Artificial Intelligence."