Skip to main content

Death and Suicide in Universal Artificial Intelligence

Part of the Lecture Notes in Computer Science book series (LNAI,volume 9782)

Abstract

Reinforcement learning (RL) is a general paradigm for studying intelligent behaviour, with applications ranging from artificial intelligence to psychology and economics. AIXI is a universal solution to the RL problem; it can learn any computable environment. A technical subtlety of AIXI is that it is defined using a mixture over semimeasures that need not sum to 1, rather than over proper probability measures. In this work we argue that the shortfall of a semimeasure can naturally be interpreted as the agent’s estimate of the probability of its death. We formally define death for generally intelligent agents like AIXI, and prove a number of related theorems about their behaviour. Notable discoveries include that agent behaviour can change radically under positive linear transformations of the reward signal (from suicidal to dogmatically self-preserving), and that the agent’s posterior belief that it will survive increases over time.

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

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-319-41649-6_3
  • 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
eBook
USD   59.99
Price excludes VAT (USA)
  • ISBN: 978-3-319-41649-6
  • 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)
Fig. 1.
Fig. 2.

Notes

  1. 1.

    For simplicity we hereafter simply refer to the environment itself as \(\nu \).

  2. 2.

    Note that \(\nu \) is not a distribution over actions, so the presence of actions in the condition of \(\nu (e_t\mid \ae _{<t})\) is an abuse of notation we adopt for simplicity.

  3. 3.

    For technical reasons we require that \(e^d \notin \mathcal {E}\).

  4. 4.

    To compare an agent’s behaviour in \(\mu \) with that in \(\mu '\), we should also augment its policy \(\pi \) so that it is defined over \((\mathcal {A}\times \mathcal {E}_d)^*\). Since actions taken once in the death-state are inconsequential, however, this modification is purely technical and for simplicity we still refer to the augmented policy as \(\pi \).

  5. 5.

    If the two formalisations predicted different behaviour, or were only applicable in incomparable environment classes, we might worry that our results were more reflective of our model choice than of any general property of intelligent agents.

References

  1. Bostrom, N.: Anthropic Bias: Observation Selection Effects in Science and Philosophy. Routledge, New York (2002)

    Google Scholar 

  2. Bostrom, N.: Superintelligence: Paths, Dangers, Strategies. Oxford University Press, Oxford (2014)

    Google Scholar 

  3. Hutter, M.: Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability. Springer, Heidelberg (2005)

    MATH  Google Scholar 

  4. Leike, J., Hutter, M.: On the computability of AIXI. In: UAI-15, pp. 464–473. AUAI Press (2015). http://arXiv.org/abs/1510.05572

  5. Li, M., Vitányi, P.M.B.: An Introduction to Kolmogorov Complexity and its Applications, 3rd edn. Springer, Heidelberg (2008)

    CrossRef  MATH  Google Scholar 

  6. Martin, J., Everitt, T., Hutter, M.: Death and suicide in universal artificial intelligence. Technical report ANU (2016). http://arXiv.org/abs/1606.00652

  7. Omohundro, S.M.: The basic AI drives. In: AGI-08, pp. 483–493. IOS Press (2008)

    Google Scholar 

  8. Soares, N., Fallenstein, B., Yudkowsky, E., Armstrong, S.: Corrigibility. In: AAAI Workshop on AI and Ethics, pp. 74–82 (2015)

    Google Scholar 

  9. Solomonoff, R.J.: Complexity-based induction systems: comparisons and convergence theorems. IEEE Trans. Inf. Theor. IT–24, 422–432 (1978)

    MathSciNet  CrossRef  MATH  Google Scholar 

  10. Veness, J., Ng, K.S., Hutter, M., Uther, W., Silver, D.: A monte carlo AIXI approximation. J. Artif. Intell. Res. 40(1), 95–142 (2011)

    MathSciNet  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Jarryd Martin .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2016 Springer International Publishing Switzerland

About this paper

Cite this paper

Martin, J., Everitt, T., Hutter, M. (2016). Death and Suicide in Universal Artificial Intelligence. In: Steunebrink, B., Wang, P., Goertzel, B. (eds) Artificial General Intelligence. AGI 2016. Lecture Notes in Computer Science(), vol 9782. Springer, Cham. https://doi.org/10.1007/978-3-319-41649-6_3

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-41649-6_3

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-41648-9

  • Online ISBN: 978-3-319-41649-6

  • eBook Packages: Computer ScienceComputer Science (R0)