An Approximation of the Universal Intelligence Measure

The Universal Intelligence Measure is a recently proposed formal definition of intelligence. It is mathematically specified, extremely general, and captures the essence of many informal definitions of intelligence. It is based on Hutter’s Universal Artificial Intelligence theory, an extension of Ray Solomonoff’s pioneering work on universal induction. Since the Universal Intelligence Measure is only asymptotically computable, building a practical intelligence test from it is not straightforward. This paper studies the practical issues involved in developing a real-world UIM-based performance metric. Based on our investigation, we develop a prototype implementation which we use to evaluate a number of different artificial agents.

[1]  Ray J. Solomonoff,et al.  A Formal Theory of Inductive Inference. Part II , 1964, Inf. Control..

[2]  Ray J. Solomonoff,et al.  Complexity-based induction systems: Comparisons and convergence theorems , 1978, IEEE Trans. Inf. Theory.

[3]  C. Watkins.  Learning from delayed rewards , 1989 .

[4]  A. M. Turing,et al.  Computing Machinery and Intelligence , 1950, The Philosophy of Artificial Intelligence.

[5]  Ming Li,et al.  An Introduction to Kolmogorov Complexity and Its Applications , 1997, Texts in Computer Science.

[6]  David L. Dowe,et al.  A Non-Behavioural, Computational Extension to the Turing Test , 1998 .

[7]  José Hernández-Orallo,et al.  Beyond the Turing Test , 2000, J. Log. Lang. Inf..

[8]  Marcus Hutter,et al.  Towards a Universal Theory of Artificial Intelligence Based on Algorithmic Probability and Sequential Decisions , 2000, ECML.

[9]  José Hernández-Orallo,et al.  A Formal Definition of Intelligence Based on an Intensional Variant of Algorithmic Complexity , 2003 .

[10]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[11]  Marcus Hutter,et al.  Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability (Texts in Theoretical Computer Science. An EATCS Series) , 2006 .

[12]  Shane Legg,et al.  Universal Intelligence: A Definition of Machine Intelligence , 2007, Minds and Machines.

[13]  Shane Legg,et al.  Temporal Difference Updating without a Learning Rate , 2007, NIPS.

[14]  P. Etoré,et al.  Adaptive Optimal Allocation in Stratified Sampling Methods , 2007, 0711.4514.

[15]  Bill Hibbard.  Bias and No Free Lunch in Formal Measures of Intelligence , 2009, J. Artif. Gen. Intell..

[16]  José Hernández-Orallo.  A (hopefully) Unbiased Universal Environment Class for Measuring Intelligence of Biological and Artificial Systems , 2009, AGI 2010.

[17]  Joel Veness,et al.  Reinforcement Learning via AIXI Approximation , 2010, AAAI.

[18]  José Hernández-Orallo,et al.  Measuring universal intelligence: Towards an anytime intelligence test , 2010, Artif. Intell..

[19]  Joel Veness,et al.  A Monte-Carlo AIXI Approximation , 2009, J. Artif. Intell. Res..

[20]  José Hernández-Orallo,et al.  Comparing Humans and AI Agents , 2011, AGI.

[21]  Julian Togelius,et al.  Measuring Intelligence through Games , 2011, ArXiv.

[22]  José Hernández-Orallo,et al.  Evaluating a Reinforcement Learning Algorithm with a General Intelligence Test , 2011, CAEPIA.