BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Getting the car up the mountain - Bayesian Reinforcement Learning 
 - Dr Torben Sell
DTSTART:20210128T131000Z
DTEND:20210128T140000Z
UID:TALK156157@talks.cam.ac.uk
CONTACT:93469
DESCRIPTION:Almost everyone is aware that computers can drive cars\, contr
 ol robots\, and beat world-class players in chess. In this talk\, we discu
 ss how this works by looking at a simple toy example. We further develop a
  statistical model which allows quantifying uncertainty in these control s
 ettings. The advantage of using the statistical model is that we can not o
 nly say which action is optimal (should the car accelerate or slow down in
  a given situation?) but also state how certain we are that a human contro
 ller would take the same action. The talk is roughly based on Sections 4 a
 nd 5 of the following preprint: https://arxiv.org/abs/2012.10943 <https://
 arxiv.org/abs/2012.10943>\, but I will largely omit the mathematical techn
 icalities.
LOCATION:ONLINE - Email organiser to request link - Details to be sent by 
 email
END:VEVENT
END:VCALENDAR