Skip to main content

Reflective Variants of Solomonoff Induction and AIXI

Part of the Lecture Notes in Computer Science book series (LNAI,volume 9205)


Solomonoff induction and AIXI model their environment as an arbitrary Turing machine, but are themselves uncomputable. This fails to capture an essential property of real-world agents, which cannot be more powerful than the environment they are embedded in; for example, AIXI cannot accurately model game-theoretic scenarios in which its opponent is another instance of AIXI.

In this paper, we define reflective variants of Solomonoff induction and AIXI, which are able to reason about environments containing other, equally powerful reasoners. To do so, we replace Turing machines by probabilistic oracle machines (stochastic Turing machines with access to an oracle). We then use reflective oracles, which answer questions of the form, “is the probability that oracle machine \(T\) outputs 1 greater than p, when run on this same oracle?” Diagonalization can be avoided by allowing the oracle to answer randomly if this probability is equal to p; given this provision, reflective oracles can be shown to exist. We show that reflective Solomonoff induction and AIXI can themselves be implemented as oracle machines with access to a reflective oracle, making it possible for them to model environments that contain reasoners as powerful as themselves.


  • Reflective oracles
  • Solomonoff induction
  • AIXI
  • Universal artificial intelligence

This is a preview of subscription content, access via your institution.

Buying options

USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-319-21365-1_7
  • Chapter length: 10 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
USD   59.99
Price excludes VAT (USA)
  • ISBN: 978-3-319-21365-1
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   79.99
Price excludes VAT (USA)


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Fallenstein, B., Soares, N.: Vingean reflection: Reliable reasoning for self-modifying agents. Tech. Rep. 2015–2, Machine Intelligence Research Institute (2015).

  2. Fallenstein, B., Taylor, J., Christiano, P.F.: Reflective oracles: A foundation for classical game theory. Tech. Rep. 2015–7, Machine Intelligence Research Institute (2015).

  3. Hutter, M.: Universal algorithmic intelligence. In: Goertzel, B., Pennachin, C. (eds.) Artificial General Intelligence, pp. 227–290. Springer, Cognitive Technologies (2007)

    Google Scholar 

  4. Hutter, M.: Open problems in universal induction & intelligence. Algorithms 2(3), 879–906 (2009)

    CrossRef  MathSciNet  Google Scholar 

  5. Legg, S., Hutter, M.: Universal intelligence. Minds and Machines 17(4), 391–444 (2007)

    CrossRef  Google Scholar 

  6. Orseau, L., Ring, M.: Space-Time Embedded Intelligence. In: Bach, J., Goertzel, B., Iklé, M. (eds.) AGI 2012. LNCS, vol. 7716, pp. 209–218. Springer, Heidelberg (2012)

    CrossRef  Google Scholar 

  7. Soares, N.: Formalizing two problems of realistic world-models. Tech. Rep. 2015–3, Machine Intelligence Research Institute (2015).

  8. Solomonoff, R.J.: A formal theory of inductive inference. Part I. Information and Control 7(1), 1–22 (1964)

    CrossRef  MathSciNet  MATH  Google Scholar 

  9. Vallinder, A.: Solomonoff Induction: A Solution to the Problem of the Priors? MA thesis, Lund University (2012).

Download references

Author information

Authors and Affiliations


Corresponding author

Correspondence to Nate Soares .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2015 Springer International Publishing Switzerland

About this paper

Cite this paper

Fallenstein, B., Soares, N., Taylor, J. (2015). Reflective Variants of Solomonoff Induction and AIXI. In: Bieger, J., Goertzel, B., Potapov, A. (eds) Artificial General Intelligence. AGI 2015. Lecture Notes in Computer Science(), vol 9205. Springer, Cham.

Download citation

  • DOI:

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-21364-4

  • Online ISBN: 978-3-319-21365-1

  • eBook Packages: Computer ScienceComputer Science (R0)