University of Cambridge > Talks.cam > Engineering Safe AI > 'Off-Switch Games' and Corrigibility

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹ️ Information

'Off-Switch Games' and Corrigibility

Download to your calendar using vCal

If you have a question about this talk, please contact Adrià Garriga Alonso .

By default, an AI system will have an incentive to prevent humans from switching it off, or otherwise interfering in its operation, as this would prevent it from maximising its reward. An AI system is ‘corrigible’ if it has an incentive to accept human corrections. Inverse Reinforcement Learning (IRL) can help mitigate this problem in some cases, but there is disagreement as to whether IRL can guarantee corrigibility in all cases.

Papers: https://arxiv.org/abs/1611.08219 https://intelligence.org/files/Corrigibility.pdf https://intelligence.org/2017/08/31/incorrigibility-in-cirl/

This talk is part of the Engineering Safe AI series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

INNER SPACE 6 KING’S PARADE CAMBRIDGE www.cambridge.inner-space.org Hybrid seminar: Clinical School Seminar Room 2 & on Zoom (see Abstract for link) https://us02web.zoom.us/j/86850511398?pwd=RDJuZlg2d1RpVDFPZmQzNzFzQWZDdz09

Other talks

Machine Learning for Spectral Geometry and Vice Versa Afternoon Break Animating urbanism: the demotic multiplicities of seeing cities digitally Title to be confirmed Tea and Coffee Break Group Work
 

© 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity