BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Safe Exploration in Reinforcement Learning - Frances Ding (Univers
 ity of Cambridge)
DTSTART:20180131T170000Z
DTEND:20180131T183000Z
UID:TALK100618@talks.cam.ac.uk
CONTACT:Adrià Garriga Alonso
DESCRIPTION:In reinforcement learning\, the learning agent always faces a 
 tradeoff between exploration and exploitation. Often\, exploration is impl
 emented as taking random actions\, but in dangerous tasks\, this can lead 
 to highly negative rewards - damage to the agent or other parts of the env
 ironment. This week we discuss methods to minimize the risks in exploratio
 n and learn good policies both safely and efficiently.\n\nSlides: https://
 valuealignment.ml/talks/2018-01-31-safe-exploration.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