BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:AI+Pizza February 2018 - Microsoft Research/University of Cambridg
 e
DTSTART:20180216T173000Z
DTEND:20180216T190000Z
UID:TALK101422@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:Speaker 1: Konstantina Palla (MSR Cambridge). \nTitle: Bayesia
 n nonparametrics for Sparse Dynamic Networks. Abstract: We propose a Bayes
 ian nonparametric prior for time-varying networks. To each node of the net
 work is associated a positive parameter\, modelling the sociability of tha
 t node. Sociabilities are assumed to evolve over time and are modelled via
  a dynamic point process model. The model is able to (a) capture smooth ev
 olution of the interaction between nodes\, allowing edges to appear/disapp
 ear over time (b) capture long term evolution of the sociabilities (c) and
  yield sparse graphs\, where the number of edges grows subquadratically wi
 th the number of nodes. The evolution of the sociabilities is described by
  a tractable time-varying gamma process. We provide some theoretical insig
 hts into the model and apply it to real world datasets.\n\nSpeaker 2: Mark
  Rowland (Cambridge university). \nTitle: Analysing Distributional Reinfor
 cement Learning. Abstract: Distributional approaches to value-based reinfo
 rcement learning use the entire distribution of returns\, rather than just
  their expected values. Recently\, these methods have been shown to yield 
 state-of-the-art performance on a variety of RL tasks. In this talk\, I'll
  recap some of the main algorithms and results in distributional reinforce
 ment learning\, and give an overview of some recent theoretical developmen
 ts (joint work with Marc G. Bellemare\, Will Dabney\, Rémi Munos\, and Ye
 e Whye Teh).\n\n\n
LOCATION:Auditorium\, Microsoft Research Ltd\, 21 Station Road\, Cambridge
 \, CB1 2FB
END:VEVENT
END:VCALENDAR