BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//University of Liverpool Computer Science Seminar System//v2//EN
BEGIN:VEVENT
DTSTAMP:20260922T191345Z
UID:Seminar-dept-386@lxserverM.csc.liv.ac.uk
ORGANIZER:CN=Lutz Oettershagen:MAILTO:Lutz.Oettershagen@liverpool.ac.uk
DTSTART:20150701T120000
DTEND:20150701T130000
SUMMARY:School Seminar Series
DESCRIPTION:Prof Ann Nowe: Speeding up Reinforcement Learning\n\nReinforcement learning describes how a learning agent can achieve optimal behaviour based on interactions with its environment and reward feedback. A limiting factor in reinforcement learning as employed in artificial intelligence is the need for an often prohibitively large number of environment samples before the agent reaches a desirable level of performance.In this talk, I will focus on two approaches that allow to speed up learning, being reward shaping and demonstrations. I will show how these two approaches can be combined allowing to leverage human input without making the assumption regarding demonstration optimality. We show experimentally that our approach requires significantly fewer demonstrations, is more robust against sub-optimality of demonstrations, and achieves much faster learning than the recently developed HAT algorithm.\n\nhttps://www.csc.liv.ac.uk/research/seminars/abstract.php?id=386
LOCATION:Ashton Lecture Theatre
END:VEVENT
END:VCALENDAR