Skip to main content
SpringerLink
Log in

Universal Algorithmic Intelligence: A Mathematical Top→Down Approach

  • Chapter
Artificial General Intelligence

Part of the book series: Cognitive Technologies ((COGTECH))

Summary

Sequential decision theory formally solves the problem of rational agents in uncertain worlds if the true environmental prior probability distribution is known. Solomonoff’s theory of universal induction formally solves the problem of sequence prediction for unknown prior distribution. We combine both ideas and get a parameter-free theory of universal Artificial Intelligence. We give strong arguments that the resulting AIXI model is the most intelligent unbiased agent possible. We outline how the AIXI model can formally solve a number of problem classes, including sequence prediction, strategic games, function minimization, reinforcement and supervised learning. The major drawback of the AIXI model is that it is un-computable. To overcome this problem, we construct a modified algorithm AIXItl that is still effectively more intelligent than any other time t and length l bounded agent. The computation time of AIXItl is of the order t·2l. The discussion includes formal definitions of intelligence order relations, the horizon problem and relations of the AIXI theory to other AI approaches.

This article grew out of the technical report [19] and summarizes and contains excerpts of the Springer book [30].

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 189.00
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 249.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 249.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Angluin D, Smith CH (1983) Inductive inference: Theory and methods. ACM Computing Surveys, 15(3):237–269.

    Article  MathSciNet  Google Scholar 

  2. Bellman RE (1957) Dynamic Programming. Princeton University Press, Princeton, NJ.

    Google Scholar 

  3. Bertsekas DP, Tsitsiklis JN (1996) Neuro-Dynamic Programming. Athena Scientific, Belmont, MA.

    MATH  Google Scholar 

  4. Chaitin GJ (1966) On the length of programs for computing finite binary sequences. Journal of the ACM, 13(4):547–5691.

    Article  MathSciNet  MATH  Google Scholar 

  5. Chaitin GJ (1975) A theory of program size formally identical to information theory. Journal of the ACM, 22(3):329–340.

    Article  MathSciNet  MATH  Google Scholar 

  6. Chaitin GJ (1991) Algorithmic information and evolution. In Solbrig O, Nicolis G (eds) Perspectives on Biological Complexity, IUBS Press, Paris.

    Google Scholar 

  7. Cheeseman P (1985) In defense of probability. In Proc. 9th International Joint Conf. on Artificial Intelligence, Morgan Kaufmann, Los Altos, CA.

    Google Scholar 

  8. Cheeseman P (1988) An inquiry into computer understanding. Computational Intelligence, 4(1):58–66.

    Google Scholar 

  9. Conte M, Tautteur G, De Falco I, Della Cioppa A, Tarantino E (1997) Genetic programming estimates of Kolmogorov complexity. In Proc. 17th International Conf. on Genetic Algorithms, Morgan Kaufmann, San Francisco, CA.

    Google Scholar 

  10. Cox RT (1946) Probability, frequency, and reasonable expectation. American Journal of Physics, 14(1):1–13.

    Article  MathSciNet  MATH  Google Scholar 

  11. Daley RP (1973) Minimal-program complexity of sequences with restricted resources. Information and Control, 23(4):301–312.

    Article  MathSciNet  MATH  Google Scholar 

  12. Daley RP (1977) On the inference of optimal descriptions. Theoretical Computer Science, 4(3):301–319.

    Article  MathSciNet  MATH  Google Scholar 

  13. Dawid AP (1984) Statistical theory. The prequential approach. Journal of the Royal Statistical Society, Series A 147:278–292.

    MathSciNet  MATH  Google Scholar 

  14. Feder M, Merhav N, Gutman M (1992) Universal prediction of individual sequences. IEEE Transactions on Information Theory, 38:1258–1270.

    Article  MathSciNet  MATH  Google Scholar 

  15. Fitting MC (1996) First-Order Logic and Automated Theorem Proving. Graduate Texts in Computer Science. Springer, Berlin.

    MATH  Google Scholar 

  16. Fudenberg D, Tirole J (1991) Game Theory. MIT Press, Cambridge, MA.

    Google Scholar 

  17. Gács P (1974) On the symmetry of algorithmic information. Soviet Mathematics Doklady, 15:1477–1480.

    MATH  Google Scholar 

  18. Hopcroft J, Motwani R, Ullman JD (2001) Introduction to Automata Theory, Language, and Computation. Addison-Wesley.

    Google Scholar 

  19. Hutter M (2000) A theory of universal artificial intelligence based on algorithmic complexity. Technical Report cs.AI/0004001 http://arxiv.org/abs/cs.AI/0004001.

    Google Scholar 

  20. Hutter M (2001) Convergence and error bounds for universal prediction of nonbinary sequences. In Proc. 12th European Conf. on Machine Learning (ECML-2001), volume 2167 of LNAI, Springer, Berlin.

    Google Scholar 

  21. Hutter M (2001) General loss bounds for universal sequence prediction. In Proc. 18th International Conf. on Machine Learning (ICML-2001).

    Google Scholar 

  22. Hutter M (2001) New error bounds for Solomonoff prediction. Journal of Computer and System Sciences, 62(4):653–667.

    Article  MathSciNet  MATH  Google Scholar 

  23. Hutter M (2001) Towards a universal theory of artificial intelligence based on algorithmic probability and sequential decisions. In Proc. 12th European Conf. on Machine Learning (ECML-2001), volume 2167 of LNAI, Springer, Berlin.

    Google Scholar 

  24. Hutter M (2001) Universal sequential decisions in unknown environments. In Proc. 5th European Workshop on Reinforcement Learning (EWRL-5).

    Google Scholar 

  25. Hutter M (2002) The fastest and shortest algorithm for all well-defined problems. International Journal of Foundations of Computer Science, 13(3):431–443.

    Article  MathSciNet  MATH  Google Scholar 

  26. Hutter M (2002) Self-optimizing and Pareto-optimal policies in general environments based on Bayes-mixtures. In Proc. 15th Annual Conf. on Computational Learning Theory (COLT 2002), volume 2375 of LNAI, Springer, Berlin.

    Google Scholar 

  27. Hutter M (2003) Convergence and loss bounds for Bayesian sequence prediction. IEEE Transactions on Information Theory, 49(8):2061–2067.

    Article  MathSciNet  Google Scholar 

  28. Hutter M (2003) On the existence and convergence of computable universal priors. In Proc. 14th International Conf. on Algorithmic Learning Theory (ALT-2003), volume 2842 of LNAI, Springer, Berlin.

    Google Scholar 

  29. Hutter M (2003) Optimality of universal Bayesian prediction for general loss and alphabet. Journal of Machine Learning Research, 4:971–1000.

    Article  MathSciNet  Google Scholar 

  30. Hutter M (2004) Universal Artificial Intelligence: Sequential Decisions based on Algorithmic Probability. Springer, Berlin. http://www.idsia.ch/~arcus/ai/uaibook.htm.

    Google Scholar 

  31. Kaelbling LP, Littman ML, Moore AW (1996) Reinforcement learning: a survey. Journal of Artificial Intelligence Research, 4:237–285.

    Google Scholar 

  32. Ko K-I (1986) On the notion of infinite pseudorandom sequences. Theoretical Computer Science, 48(1):9–33.

    Article  MathSciNet  MATH  Google Scholar 

  33. Kolmogorov AN (1965) Three approaches to the quantitative definition of information. Problems of Information and Transmission, 1(1):1–7.

    MathSciNet  Google Scholar 

  34. Kumar PR, Varaiya PP (1986). Stochastic Systems: Estimation, Identification, and Adaptive Control. Prentice Hall, Englewood Cliffs, NJ.

    MATH  Google Scholar 

  35. Kwee I, Hutter M, Schmidhuber J (2001) Gradient-based reinforcement planning in policy-search methods. In Proc. 5th European Workshop on Reinforcement Learning (EWRL-5).

    Google Scholar 

  36. Kwee I, Hutter M, Schmidhuber J (2001) Market-based reinforcement learning in partially observable worlds. In Proc. International Conf. on Artificial Neural Networks (ICANN-2001), volume 2130 of LNCS, Springer, Berlin.

    Google Scholar 

  37. Levin L (1973) Universal sequential search problems. Problems of Information Transmission, 9:265–266.

    Google Scholar 

  38. Levin L (1974) Laws of information conservation (non-growth) and aspects of the foundation of probability theory. Problems of Information Transmission, 10(3):206–210.

    Google Scholar 

  39. Li M, Vitányi PMB (1991) Learning simple concepts under simple distributions. SIAM Journal on Computing, 20(5):911–935.

    Article  MathSciNet  MATH  Google Scholar 

  40. Li M, Vitányi PMB (1992) Inductive reasoning and Kolmogorov complexity. Journal of Computer and System Sciences, 44:343–384.

    Article  MathSciNet  MATH  Google Scholar 

  41. Li M, Vitányi PMB (1992). Philosophical issues in Kolmogorov complexity (invited lecture). In Proceedings on Automata, Languages and Programming (ICALP-92), Springer, Berlin.

    Google Scholar 

  42. Li M, Vitányi PMB (1997) An Introduction to Kolmogorov Complexity and its Applications. Springer, Berlin, 2nd edition.

    MATH  Google Scholar 

  43. Littlestone N, Warmuth MK (1989) The weighted majority algorithm. In 30th Annual Symposium on Foundations of Computer Science.

    Google Scholar 

  44. Littlestone N, Warmuth MK (1994) The weighted majority algorithm. Information and Computation, 108(2):212–261.

    Article  MathSciNet  MATH  Google Scholar 

  45. Lucas, JR (1961) Minds, machines, and Gödel. Philosophy, 36:112–127.

    Article  Google Scholar 

  46. Michie D (1966) Game-playing and game-learning automata. In Fox, E (ed) Advances in Programming and Non-Numerical Computation, Pergamon, New York.

    Google Scholar 

  47. Von Neumann J, Morgenstern O (1944) Theory of Games and Economic Behavior. Princeton University Press, Princeton, NJ.

    MATH  Google Scholar 

  48. Osborne MJ, Rubenstein A (1994) A Course in Game Theory. MIT Press, Cambridge, MA.

    Google Scholar 

  49. Penrose R (1989) The Emperor’s New Mind. Oxford University Press, Oxford.

    Google Scholar 

  50. Penrose R (1994) Shadows of the Mind, A Search for the Missing Science of Consciousness. Oxford University Press, Oxford.

    Google Scholar 

  51. Pintado X, Fuentes E (1997) A forecasting algorithm based on information theory. In Tsichritzis D (ed) Objects at Large, Technical Report, Université de Genève.

    Google Scholar 

  52. Rissanen JJ (1989) Stochastic Complexity in Statistical Inquiry. World Scientific, Singapore.

    MATH  Google Scholar 

  53. Russell S, Norvig P (2003) Artificial Intelligence. A Modern Approach. Prentice-Hall, Englewood Cliffs, NJ, 2nd edition.

    Google Scholar 

  54. Schmidhuber J (1997) Discovering neural nets with low Kolmogorov complexity and high generalization capability. Neural Networks, 10(5):857–873.

    Article  Google Scholar 

  55. Schmidhuber J (2002) The speed prior: A new simplicity measure yielding near-optimal computable predictions. In Proc. 15th Conf. on Computational Learning Theory (COLT-2002), volume 2375 of LNAI, Springer, Berlin.

    Google Scholar 

  56. Schmidhuber J (2003) Bias-optimal incremental problem solving. In Becker S, Thrun S, Obermayer K (eds) Advances in Neural Information Processing Systems 15, MIT Press, Cambridge, MA.

    Google Scholar 

  57. Schmidhuber J (2004) Optimal ordered problem solver. Machine Learning, 54(3):211–254, also this volume.

    Article  MATH  Google Scholar 

  58. Schmidhuber J, Zhao J, Wiering MA (1997) Shifting inductive bias with success-story algorithm, adaptive Levin search, and incremental self-improvement. Machine Learning, 28:105–130.

    Article  Google Scholar 

  59. Schmidt M (1999) Time-bounded Kolmogorov complexity may help in search for extra terrestrial intelligence (SETI). Bulletin of the European Association for Theoretical Computer Science, 67:176–180.

    MATH  Google Scholar 

  60. Shoenfield JR (1967) Mathematical Logic. Addison-Wesley, Reading, MA.

    MATH  Google Scholar 

  61. Solomonoff R (1964) A formal theory of inductive inference: Parts 1 and 2. Information and Control, 7:1–22 and 224–254.

    Article  MathSciNet  MATH  Google Scholar 

  62. Solomonoff R (1978) Complexity-based induction systems: Comparisons and convergence theorems. IEEE Transaction on Information Theory, IT-24:422–432.

    Article  MathSciNet  Google Scholar 

  63. Solomonoff R (1986) The application of algorithmic probability to problems in artificial intelligence. In Kanal L, Lemmer J (eds) Uncertainty in Artificial Intelligence, Elsevier Science/North-Holland, Amsterdam.

    Google Scholar 

  64. Solomonoff R (1997) The discovery of algorithmic probability. Journal of Computer and System Sciences, 55(1):73–88.

    Article  MathSciNet  MATH  Google Scholar 

  65. Solomonoff R (1999) Two kinds of probabilistic induction. Computer Journal, 42(4):256–259.

    Article  MATH  Google Scholar 

  66. Sutton R, Barto A (1998) Reinforcement Learning: An Introduction. MIT Press, Cambridge, MA.

    Google Scholar 

  67. Valiant LG (1984) A theory of the learnable. Communications of the ACM, 27(11):1134–1142.

    Article  MATH  Google Scholar 

  68. Vovk VG (1992) Universal forecasting algorithms. Information and Computation, 96(2):245–277.

    Article  MathSciNet  MATH  Google Scholar 

  69. Vovk VG, Watkins C (1998) Universal portfolio selection. In Proc. 11th Conf. on Computational Learning Theory (COLT-98), ACM Press, New York.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. IDSIA, Galleria 2, CH-6928, Manno-Lugano, Switzerland

    Marcus Hutter

  2. RSISE/ANU/NICTA, Canberra, ACT, 0200, Australia

    Marcus Hutter

Authors
  1. Marcus Hutter
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. AGIRI — Artificial General Intelligence Research Institute, 1405 Bernerd Place, Rockville, MD, 20851, USA

    Ben Goertzel  & Cassio Pennachin  & 

Rights and permissions

Reprints and permissions

Copyright information

© 2007 Springer-Verlag Berlin Heidelberg

About this chapter

Cite this chapter

Hutter, M. (2007). Universal Algorithmic Intelligence: A Mathematical Top→Down Approach. In: Goertzel, B., Pennachin, C. (eds) Artificial General Intelligence. Cognitive Technologies. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-68677-4_8

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-68677-4_8

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-23733-4

  • Online ISBN: 978-3-540-68677-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation