BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Decision Theory for AI safety - Richard Ngo (University of Cambrid
 ge)
DTSTART:20180207T170000Z
DTEND:20180207T183000Z
UID:TALK100972@talks.cam.ac.uk
CONTACT:Adrià Garriga Alonso
DESCRIPTION:Decision theory is the study of how rational agents should act
  in idealised situations. While it has important implications for the desi
 gn and analysis of AI agents\, there are still major unresolved problems. 
 The two leading decision theories - Causal Decision Theory and Evidential 
 Decision Theory - both seem to fail in some cases. Functional Decision The
 ory\, an alternative proposed by researchers at MIRI\, has some appealing 
 properties but remains underspecified. In this talk I will explore the imp
 ortance of decision theory to AI safety\, explain the three theories menti
 oned above\, and evaluate various objections which have been raised\, and 
 responses to them.\n\nYou can read more about the topic here: https://arxi
 v.org/abs/1710.05060\n\nTalk slides:\nhttps://docs.google.com/presentation
 /d/1hoXUiEbGhzGcC2JkmcMPEpXgXL0Rj19hQdJn46zv1H8/edit#slide=id.p\n\nhttps:/
 /valuealignment.ml/talks/2018-02-07-decision-theory-ai-safety.pdf
LOCATION: Cambridge University Engineering Department\, CBL Seminar room B
 E4-38.  For directions see http://learning.eng.cam.ac.uk/Public/Directions
END:VEVENT
END:VCALENDAR