BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Non-Stationary Representation Learning in Sequential Linear Bandit
 s - Yuzhen Qin\, University of California\, Riverside
DTSTART:20220616T150000Z
DTEND:20220616T160000Z
UID:TALK175538@talks.cam.ac.uk
CONTACT:Xiaodong Cheng
DESCRIPTION:Humans are naturally endowed with the ability to learn and tra
 nsfer experience to later unseen tasks. One of the key mechanisms enabling
  such versatility is the abstraction of past experience into a ‘basis se
 t’ of simpler representations that can be used to construct new strategi
 es much more efficiently in future complex environments. What can we learn
  from humans when we design decision-making strategies? In this talk\, we 
 will talk about representation learning for multi-task decision-making in 
 nonstationary environments. We consider the framework of sequential linear
  bandits\, where the agent performs a series of tasks drawn from different
  environments. The embeddings of tasks in each environment share a low-dim
 ensional feature extractor called representation\, and representations are
  different across environments. We propose an online algorithm that facili
 tates efficient decision-making by learning and transferring non-stationar
 y representations in an adaptive fashion.\n
LOCATION:JBD seminar room\, Department of Engineering / Online (Zoom)
END:VEVENT
END:VCALENDAR