Skip to main content
padlock icon - secure page this page is secure

Utility function security in artificially intelligent agents

Buy Article:

$60.00 + tax (Refund Policy)

The notion of ‘wireheading’, or direct reward centre stimulation of the brain, is a well-known concept in neuroscience. In this paper, we examine the corresponding issue of reward (utility) function integrity in artificially intelligent machines. We survey the relevant literature and propose a number of potential solutions to ensure the integrity of our artificial assistants. Overall, we conclude that wireheading in rational self-improving optimisers above a certain capacity remains an unsolved problem despite opinion of many that such machines will choose not to wirehead. A relevant issue of literalness in goal setting also remains largely unsolved and we suggest that the development of a non-ambiguous knowledge transfer language might be a step in the right direction.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
No Article Media
No Metrics

Keywords: counterfeit utility; literalness; reward function; wireheading

Document Type: Research Article

Affiliations: Department of Computer Engineering and Computer Science, University of Louisville, Louisville, KY, USA

Publication date: July 3, 2014

More about this publication?
  • Access Key
  • Free content
  • Partial Free content
  • New content
  • Open access content
  • Partial Open access content
  • Subscribed content
  • Partial Subscribed content
  • Free trial content
Cookie Policy
X
Cookie Policy
Ingenta Connect website makes use of cookies so as to keep track of data that you have filled in. I am Happy with this Find out more