BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Benefits and Shortcomings of Assistance - Dmitrii Krasheninnikov a
 nd Lauro Langosco\, University of Cambridge
DTSTART:20220622T100000Z
DTEND:20220622T113000Z
UID:TALK175706@talks.cam.ac.uk
CONTACT:Elre Oldewage
DESCRIPTION:Assistance games (also known as cooperative inverse RL) enable
  a single RL policy to both infer human preferences and act such that they
  are optimized. The idea is to model the human as a part of the environmen
 t\, and the true reward function as a latent variable in the environment t
 hat the agent may make inferences about. Our talk will introduce the assis
 tance paradigm\, compare it to reward learning\, and discuss its flaws in 
 the context of AI Alignment.
LOCATION:Cambridge University Engineering Department\, CBL Seminar room BE
 4-38
END:VEVENT
END:VCALENDAR