Skip to main content
SpringerLink
Log in

Inferring Human Values for Safe AGI Design

  • Conference paper
  • First Online:
Artificial General Intelligence (AGI 2015)

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

Included in the following conference series:

Abstract

Aligning goals of superintelligent machines with human values is one of the ways to pursue safety in AGI systems. To achieve this, it is first necessary to learn what human values are. However, human values are incredibly complex and cannot easily be formalized by hand. In this work, we propose a general framework to estimate the values of a human given its behavior.

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 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight 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. Dewey, D.: Learning what to value. In: Schmidhuber, J., Thórisson, K.R., Looks, M. (eds.) AGI 2011. LNCS, vol. 6830, pp. 309–314. Springer, Heidelberg (2011)

    Chapter  Google Scholar 

  2. Hibbard, B.: Avoiding unintended AI behaviors. In: Bach, J., Goertzel, B., Iklé, M. (eds.) AGI 2012. LNCS, vol. 7716, pp. 107–116. Springer, Heidelberg (2012)

    Chapter  Google Scholar 

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

    Google Scholar 

  4. Muehlhauser, L., Helm, L.: The singularity and machine ethics. In: Eden, A.H., Moor, J.H., Sraker, J.H., Steinhart, E. (eds.) Singularity Hypotheses, pp. 101–126. Springer, Heidelberg (2012). The Frontiers Collection

    Chapter  Google Scholar 

  5. Ng, A.Y., Russell, S.J.: Algorithms for inverse reinforcement learning. In: Proceedings of the Seventeenth International Conference on Machine Learning, ICML 2000, pp. 663–670. Morgan Kaufmann Publishers Inc., San Francisco (2000)

    Google Scholar 

  6. Schmidhuber, J.: The speed prior: a new simplicity measure yielding near-optimal computable predictions. In: Kivinen, J., Sloan, R.H. (eds.) COLT 2002. LNCS (LNAI), vol. 2375, p. 216. Springer, Heidelberg (2002)

    Chapter  Google Scholar 

  7. Soares, N.: The value learning problem. Tech. rep., Machine Intelligence ResearchInstitute, Berkeley, CA (2015)

    Google Scholar 

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

    Article  MathSciNet  Google Scholar 

  9. Yudkowsky, E.: Complex value systems in friendly AI. In: Schmidhuber, J., Thórisson, K.R., Looks, M. (eds.) AGI 2011. LNCS, vol. 6830, pp. 388–393. Springer, Heidelberg (2011)

    Chapter  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, Ozyegin University, Istanbul, Turkey

    Can Eren Sezener

Authors
  1. Can Eren Sezener
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Can Eren Sezener .

Editor information

Editors and Affiliations

  1. Reykjavik University, Reykjavik, Iceland

    Jordi Bieger

  2. Hong Kong Polytechnic University, Hong Kong, Hong Kong SAR

    Ben Goertzel

  3. Mechanics and Optics, Saint Petersburg State University of Information Technologies, St. Petersburg, Russia

    Alexey Potapov

Rights and permissions

Reprints and permissions

Copyright information

© 2015 Springer International Publishing Switzerland

About this paper

Cite this paper

Sezener, C.E. (2015). Inferring Human Values for Safe AGI Design. In: Bieger, J., Goertzel, B., Potapov, A. (eds) Artificial General Intelligence. AGI 2015. Lecture Notes in Computer Science(), vol 9205. Springer, Cham. https://doi.org/10.1007/978-3-319-21365-1_16

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-21365-1_16

  • 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)

Publish with us

Policies and ethics

Search

Navigation