BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Adversarial attacks against reinforcement learning agents - Christ
 opher Goh\, Hughes Hall College
DTSTART:20201125T190000Z
DTEND:20201125T193000Z
UID:TALK154369@talks.cam.ac.uk
CONTACT:Matthew Ireland
DESCRIPTION:Reinforcement learning agents have progressed by leaps and bou
 nds over the last few years. We now have self-driving cars from Tesla\,  c
 ompetitive game playing agents from OpenAI and Deepmind and many more. \n\
 nWhile our knowledge about such technologies has improved\, so too has our
  knowledge about the inherent weaknesses in such systems.\n\nIn this prese
 ntation\, I will be discussing how reinforcement learning agents work\, ho
 w adversarial attacks take advantage of weaknesses to fool these agents\, 
 and some of the defences we have against such attacks.  
LOCATION:Online\, via MS Teams
END:VEVENT
END:VCALENDAR