Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability

Front Cover
Springer Science & Business Media, 2005 - Computers - 278 pages
0 Reviews
Personal motivation. The dream of creating artificial devices that reach or outperform human inteUigence is an old one. It is also one of the dreams of my youth, which have never left me. What makes this challenge so interesting? A solution would have enormous implications on our society, and there are reasons to believe that the AI problem can be solved in my expected lifetime. So, it's worth sticking to it for a lifetime, even if it takes 30 years or so to reap the benefits. The AI problem. The science of artificial intelligence (AI) may be defined as the construction of intelligent systems and their analysis. A natural definition of a system is anything that has an input and an output stream. Intelligence is more complicated. It can have many faces like creativity, solving prob lems, pattern recognition, classification, learning, induction, deduction, build ing analogies, optimization, surviving in an environment, language processing, and knowledge. A formal definition incorporating every aspect of intelligence, however, seems difficult. Most, if not all known facets of intelligence can be formulated as goal driven or, more precisely, as maximizing some utility func tion. It is, therefore, sufficient to study goal-driven AI; e. g. the (biological) goal of animals and humans is to survive and spread. The goal of AI systems should be to be useful to humans.
  

What people are saying - Write a review

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

Contents

Uncertainty 29
30
2 Prefix coding of natural numbers and strings
34
14 Kolmogorovs axioms of probability theory
41
25 Posterior convergence of M to p
48
31 MartinL6f random sequences
54
Universal Sequence Prediction
65
8 Convergence of random sequences
71
36 Error bound
83
1 The agent model
126
The Universal Algorithmic Agent AIXI
141
12 We expect AIXI to be universally optimal
146
30 Discounted Alp model and value
159
Important Environmental Classes 185
184
Computational Aspects
210
1 The fastest algorithm
211
8 Effective intelligence order relation
226

59 Instantaneous loss bound
91
64 Lower error bound
97
65 Pareto optimality
99
Agents in Known Probabilistic Environments
125
Discussion
231
Bibliography 251
250
Index
265
Copyright

Common terms and phrases

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."