BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//University of Liverpool Computer Science Seminar System//v2//EN
BEGIN:VEVENT
DTSTAMP:20260921T003215Z
UID:Seminar-robotics-710@lxserverM.csc.liv.ac.uk
ORGANIZER:CN=Matt webster:MAILTO:M.Webster@liverpool.ac.uk
DTSTART:20180410T110000
DTEND:20180410T120000
SUMMARY:Robotics and Autonomous Systems Series
DESCRIPTION:Richard Klima: Model-Based Reinforcement Learning under Periodical Observability\n\nThe uncertainty induced by unknown attacker locations is one of the problems in deploying AI methods to security domains. We study a model with partial observability of the attacker location and propose a novel reinforcement learning method using partial information about attacker behaviour coming from the system. This method is based on deriving beliefs about underlying states using Bayesian inference. These beliefs are then used in the QMDP algorithm. We particularly design the algorithm for spatial security games, where the defender faces intelligent and adversarial opponents.\n\nhttps://www.csc.liv.ac.uk/research/seminars/abstract.php?id=710
LOCATION:
END:VEVENT
END:VCALENDAR