BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Fast  Adaptation with  Meta-Reinforcement  Learning  for  Trust Mo
 delling  in  Human-Robot Interaction - Speaker to be confirmed
DTSTART:20190701T131500Z
DTEND:20190701T140000Z
UID:TALK127267@talks.cam.ac.uk
CONTACT:Hatice Gunes
DESCRIPTION:In socially assistive robotics\, an important research area is
  the development of adaptation techniques and their effect on human-robot 
 interaction. We present a  meta-learning based policy gradient method for 
 addressing the problem of adaptation in human-robot interaction and also i
 nvestigate its role as a mechanism for trust modelling.\nBy building an es
 cape room scenario in mixed reality with a robot\, we test our hypothesis 
 that bi-directional trust can be influenced by different adaptation algori
 thms. We found that our proposed model increased the perceived trustworthi
 ness of the robot and influenced the dynamics of gaining human's trust. Ad
 ditionally\, participants evaluated that the robot perceived them as more 
 trustworthy during the interactions with the meta-learning based adaptatio
 n compared to the previously studied statistical adaptation model.\n\nBio:
 \n(Alex) Yuan Gao received his Master's degree in machine learning with a 
 minor in mathematics from the University of Helsinki and is currently a Ph
 D candidate at Uppsala University. He is interested in developing AI-drive
 n robots that can think and feel like real humans (e.g. Ex Machina). In pa
 rticular\, he is interested in deep/reinforcement/neuro-based learning app
 roaches for robotic perception\, control\, and physical modelling of the r
 obot’s environment\, which can help us to understand ourselves and build
  a unified learning structure for an adaptive\, efficient and robust compl
 ex robotic system. Currently\, he is working on projects that can fill the
  gap between deep reinforcement learning and social robotics.\n
LOCATION:SS03 Meeting Room\, Computer Laboratory
END:VEVENT
END:VCALENDAR