Abstract
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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Dowe, D.L., Hajek, A.R.: A non-behavioural, computational extension to the Turing Test. In: Intl. Conf. on Computational Intelligence & Multimedia Applications (ICCIMA 1998), Gippsland, Australia, pp. 101–106 (February 1998)
Étoré, P., Jourdain, B.: Adaptive optimal allocation in stratified sampling methods. Methodology and Computing in Applied Probability 12(3), 335–360 (2010)
Hernández-Orallo, J.: Beyond the Turing Test. J. Logic, Language & Information 9(4), 447–466 (2000)
Hernández-Orallo, J., Dowe, D.L.: Measuring universal intelligence: Towards an anytime intelligence test. Artificial Intelligence 174(18), 1508–1539 (2010)
Hernández-Orallo, J., Minaya-Collado, N.: A formal definition of intelligence based on an intensional variant of Kolmogorov complexity. In: Proc. Intl. Symposium of Engineering of Intelligent Systems (EIS 1998), pp. 146–163. ICSC Press (1998)
Hernández-Orallo, J.: A (hopefully) Non-biased Universal Environment Class for Measuring Intelligence of Biological and Artificial Systems. In: Baum, E., Hutter, M., Kitzelmann, E. (eds.) 3rd Intl. Conf. on Artificial General Intelligence, pp. 182–183. Atlantis Press (2010)
Hibbard, B.: Bias and no free lunch in formal measures of intelligence. Journal of Artificial General Intelligence 1(1), 54–61 (2009)
Hutter, M.: Towards a universal theory of artificial intelligence based on algorithmic probability and sequential decisions. In: Flach, P.A., De Raedt, L. (eds.) ECML 2001. LNCS (LNAI), vol. 2167, pp. 226–238. Springer, Heidelberg (2001)
Hutter, M.: Universal Artificial Intelligence: Sequential Decisions based on Algorithmic Probability, 300 pages. Springer, Berlin (2005), http://www.hutter1.net/ai/uaibook.htm
Hutter, M., Legg, S.: Temporal difference updating without a learning rate. In: Advances in Neural Information Processing Systems, vol. 20, pp. 705–712. MIT Press, Cambridge (2008)
Insa-Cabrera, J., Dowe, D.L., España-Cubillo, S., Hernández-Lloreda, M.V., Hernández-Orallo, J.: Comparing Humans and AI Agents. In: Schmidhuber, J., Thórisson, K.R., Looks, M. (eds.) AGI 2011. LNCS (LNAI), vol. 6830, pp. 122–132. Springer, Heidelberg (2011)
Insa-Cabrera, J., Dowe, D.L., Hernández-Orallo, J.: Evaluating a reinforcement learning algorithm with a general intelligence test. In: Lozano, J.A., Gámez, J.A., Moreno, J.A. (eds.) CAEPIA 2011. LNCS, vol. 7023, pp. 1–11. Springer, Heidelberg (2011)
Legg, S., Hutter, M.: Universal intelligence: A definition of machine intelligence. Minds and Machines 17(4), 391–444 (2007)
Li, M., Vitányi, P.M.B.: An introduction to Kolmogorov complexity and its applications, 3rd edn. Springer (2008)
Mahoney, M.: Generic compression benchmark (2008), http://www.mattmahoney.net/dc/uiq
Schaul, T., Togelius, J., Schmidhuber, J.: Measuring Intelligence through Games. ArXiv e-prints (September 6, 2011), http://arxiv.org/abs/1109.1314v1
Solomonoff, R.J.: A formal theory of inductive inference: Part 1 and 2. Inform. Control 7(1-22), 224–254 (1964)
Solomonoff, R.J.: Complexity-based induction systems: comparisons and convergence theorems. IEEE Trans. Information Theory IT-24, 422–432 (1978)
Sutton, R., Barto, A.: Reinforcement learning: An introduction. MIT Press, Cambridge (1998)
Turing, A.M.: Computing Machinery and Intelligence. Mind 59, 433–460 (1950)
Veness, J., Ng, K.S., Hutter, M., Silver, D.: Reinforcement learning via AIXI approximation. In: Proc. 24th AAAI Conference on Artificial Intelligence, pp. 605–611. AAAI Press, Atlanta (2010)
Veness, J., Ng, K.S., Hutter, M., Uther, W., Silver, D.: A Monte-Carlo AIXI Approximation. Journal of Artificial Intelligence Research (JAIR) 40(1), 95–142 (2011)
Watkins, C.J.C.H.: Learning from Delayed Rewards. PhD thesis, King’s College, Oxford (1989)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Legg, S., Veness, J. (2013). An Approximation of the Universal Intelligence Measure. In: Dowe, D.L. (eds) Algorithmic Probability and Friends. Bayesian Prediction and Artificial Intelligence. Lecture Notes in Computer Science, vol 7070. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-44958-1_18
Download citation
DOI: https://doi.org/10.1007/978-3-642-44958-1_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-44957-4
Online ISBN: 978-3-642-44958-1
eBook Packages: Computer ScienceComputer Science (R0)