One Decade of Universal Artificial Intelligence

@article{Hutter2012OneDO,
  title={One Decade of Universal Artificial Intelligence},
  author={Marcus Hutter},
  journal={ArXiv},
  year={2012},
  volume={abs/1202.6153}
}
The first decade of this century has seen the nascency of the first mathematical theory of general artificial intelligence. This theory of Universal Artificial Intelligence (UAI) has made significant contributions to many theoretical, philosophical, and practical AI questions. In a series of papers culminating in book (Hutter, 2005), an exciting sound and complete mathematical model for a super intelligent agent (AIXI) has been developed and rigorously analyzed. While nowadays most AI… 
An Overview of Approaches Evaluating Intelligence of Artificial Systems
TLDR
The Algorithmic Intelligence Quotient test, derived from Universal Intelligence definition, is currently the most suitable candidate for a practical intelligence evaluation method of artificial systems, although the test has several known limitations.
The search for (artificial) intelligence, in capitalism
Artificial intelligence is being touted as a new wave of machinic processing and productive potential. Building on concepts starting with the invention of the term artificial intelligence in the
Can Intelligence Explode?
TLDR
This course will provide a more careful treatment of what intelligence actually is, separate speed from intelligence explosion, compare what super-intelligent participants and classical human observers might experience and do, discuss immediate implications for the diversity and value of life, consider possible bounds on intelligence, and contemplate intelligences right at the singularity.
The mirror for (artificial) intelligence: Working in whose reflection?
TLDR
The discussion paper argues that a series of machinic and technological invention and related experiments show how machines facilitate not only the processes of normalization of what are considered intelligent behaviours, via both human and machinic intelligence, but also facilitate and enable the integration of autonomous machines into everyday work and life.
The mirror for (artificial) intelligence in capitalism
‘The mirror for (artificial) intelligence in capitalism’ expands on the historical episodes outlined in the article by Engster and Moore in the current Special Issue, to develop the historical
Foundations of Induction
TLDR
Solomonoff’s formal, general, complete, and essentially unique theory of universal induction and prediction, rooted in algorithmic information theory and based on the philosophical and technical ideas of Ockham, Epicurus, Bayes, Turing, and Kolmogorov, essentially constitutes a conceptual solution to the induction problem.
Subjective Reality and Strong Artificial Intelligence
TLDR
This paper formulate the model of the perception of external world which may be used for the description of perceptual activity of intelligent beings and shows how the methodology of subjective reality may be use for the creation of different types of Strong AI systems.
Strengths and potential of the SP theory of intelligence in general, human-like artificial intelligence
TLDR
There are reasons to believe that a mature version of the SP system may attain full GHLAI in diverse aspects of intelligence and in the representation of diverse kinds of knowledge.
The Foundations of Solomonoff Prediction
R.J. Solomonoff’s theory of Prediction assembles notions from information theory, confirmation theory and computability theory into the specification of a supposedly all-encompassing objective method
...
...

References

SHOWING 1-10 OF 99 REFERENCES
Universal Artificial Intelligence
  • Dr. Marcus Hutter
  • Computer Science
    Texts in Theoretical Computer Science An EATCS Series
  • 2005
TLDR
UAI is an increasingly well-studied foundational theory for artificial intelligence, based on ancient principles in the philosophy of science and modern developments in information and probability theory, that provides a theoretically optimal agent AIXI and principled ideas for constructing practical autonomous agents.
Universal Intelligence: A Definition of Machine Intelligence
TLDR
A number of well known informal definitions of human intelligence are taken, and mathematically formalised to produce a general measure of intelligence for arbitrary machines that formally captures the concept of machine intelligence in the broadest reasonable sense.
An Approximation of the Universal Intelligence Measure
TLDR
This paper studies the practical issues involved in developing a real-world UIM-based performance metric and develops a prototype implementation which is used to evaluate a number of different artificial agents.
Logics in Artificial Intelligence
TLDR
This book's goal, to serve as an elementary text and reference work on the applications of nonstandard logics to artificial intelligence, is somewhat more restrictive than what was inferred from the rifle, namely uses of logic in AI.
Theoretical Foundations of Artificial General Intelligence
This book is a collection of writings by active researchers in the field of Artificial General Intelligence, on topics of central importance in the field. Each chapter focuses on one theoretical
Can Intelligence Explode?
TLDR
This course will provide a more careful treatment of what intelligence actually is, separate speed from intelligence explosion, compare what super-intelligent participants and classical human observers might experience and do, discuss immediate implications for the diversity and value of life, consider possible bounds on intelligence, and contemplate intelligences right at the singularity.
A Philosophical Treatise of Universal Induction
TLDR
The case for Solomonoff Induction is argued, a formal inductive framework which combines algorithmic information theory with the Bayesian framework and how this approach addresses many issues that have plagued other inductive systems, such as the black ravens paradox and the confirmation problem.
Open Problems in Universal Induction & Intelligence
TLDR
The state of the art in universal induction and its extension to universal intelligence is described and the state-of-the-art is described only in passing and the reader is referred to the literature.
...
...