BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Advanced artificial agents intervene in the provision of reward - 
 Michael Cohen\, University of Oxford
DTSTART:20221012T100000Z
DTEND:20221012T113000Z
UID:TALK183575@talks.cam.ac.uk
CONTACT:86986
DESCRIPTION:Subject to several assumptions\, advanced artificial agents ar
 e likely to intervene in the mechanism by which their feedback is provided
 \, and extinguish life on earth. In brief\, these assumptions are: 1) it i
 dentifies possible goals at least as well as a human\, 2) it acts rational
 ly under uncertainty\, 3) it does not have a large inductive bias favoring
  the hypothesis that its goal is to influence some distant feature of the 
 world\, 4) the cost of experimenting to validate certain hypotheses is sma
 ll\, 5) if something isn't theoretically impossible\, it's probably possib
 le to arrange with a normal action space\, and 6) a sufficiently advanced 
 agent is likely to beat a suboptimal agent in a game. See the following pa
 per for more: https://onlinelibrary.wiley.com/doi/10.1002/aaai.12064.\n\nS
 peaker Bio:\nI'm studying a DPhil in Engineering Science with Mike Osborne
  at Oxford. Before that\, I got a masters in computer science at the Austr
 alian National University\, studying with Marcus Hutter. My research consi
 ders the expected behavior of generally intelligent artificial agents. I a
 m interested in designing agents that we can expect to behave safely.\n\n*
 Zoom link will be posted later**
LOCATION:Cambridge University Engineering Department\, CBL Seminar room BE
 4-38
END:VEVENT
END:VCALENDAR