Abstract
I. J. Good’s intelligence explosion theory predicts that ultraintelligent agents will undergo a process of repeated self-improvement; in the wake of such an event, how well our values are fulfilled would depend on the goals of these ultraintelligent agents. With this motivation, we examine ultraintelligent reinforcement learning agents. Reinforcement learning can only be used in the real world to define agents whose goal is to maximize expected rewards, and since this goal does not match with human goals, AGIs based on reinforcement learning will often work at cross-purposes to us. To solve this problem, we define value learners, agents that can be designed to learn and maximize any initially unknown utility function so long as we provide them with an idea of what constitutes evidence about that utility function.
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
Good, I.J.: Speculations Concerning the First Ultraintelligent Machine. In: Alt, F.L., Rubinoff, M. (eds.) Advances in Computers, vol. 6, pp. 31–88 (1965)
Hay, N.: Optimal Agents (2007), http://www.cs.auckland.ac.nz/~nickjhay/honours.revamped.pdf
Hutter, M.: Universal algorithmic intelligence: A mathematical top-down approach. In: Artificial General Intelligence, pp. 227–290. Springer, Berlin (2007)
Hutter, M.: http://www.hutter1.net/ai/uaibook.htm#oneline
Omohundro: The Nature of Self-Improving Artificial Intelligence, http://omohundro.files.wordpress.com/2009/12/nature_of_self_improving_ai.pdf
Omohundro, S.: The basic AI drives. In: Wang, P., Goertzel, B., Franklin, S. (eds.) Proceedings of the First AGI Conference on Frontiers in Artificial Intelligence and Applications, vol. 171. IOS Press, Amsterdam (2008)
Russell, S., Norvig, P.: AI A Modern Approach. Prentice-Hall, Englewood Cliffs (1995)
Yudkowsky, E.: Artificial intelligence as a positive and negative factor in global risk. In: Bostrom, N. (ed.) Global Catastrophic Risks. Oxford University Press, Oxford (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dewey, D. (2011). Learning What to Value. In: Schmidhuber, J., ThĂłrisson, K.R., Looks, M. (eds) Artificial General Intelligence. AGI 2011. Lecture Notes in Computer Science(), vol 6830. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-22887-2_35
Download citation
DOI: https://doi.org/10.1007/978-3-642-22887-2_35
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-22886-5
Online ISBN: 978-3-642-22887-2
eBook Packages: Computer ScienceComputer Science (R0)