BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Towards ad hoc interactions with robots - Subramanian Ramamoorthy\
 , University of Edinburgh
DTSTART:20121023T130000Z
DTEND:20121023T140000Z
UID:TALK40945@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:A primary motivation for work within my group is the notion of
  autonomous agents that can interact\, robustly over the long term\, with 
 an incompletely known environment that continually changes. In this talk I
  will describe results from a few different projects that attempt to addre
 ss key aspects of this big question.\n\nI will begin by looking at how tas
 k encodings can be made effective using qualitative (geometric) structure 
 in the strategy space. Using examples that may be familiar to many machine
  learning researchers – such as control of an inverted pendulum and bipe
 dal walkers – we will explore this connection between the geometric stru
 cture of solutions and strategies for dealing with a continually changing 
 task context. The key result here would be regarding ways to combine explo
 itation of 'natural' dynamics with the benefits of active planning.\n\nCan
  there be similarly flexible encodings for more general decision problems\
 , beyond the domain of robot control? I will describe recent results from 
 our work on policy reuse and transfer learning\, demonstrating how it is p
 ossible to construct agents that can learn to adapt\, through a process of
  belief updating based on policy performance\, to a changing task context 
 including the case where the change may be induced by other decision makin
 g agents. \n\nFinally\, building on this theme of making decisions in the 
 presence of other decision making agents\, I will briefly describe results
  from our recent experiments in human-robot interaction where agents must 
 learn to influence the behaviour of other agents in order to achieve their
  task. This experiment is a step towards general and implementable models 
 of ad hoc interaction where agents learn from experience to shape aspects 
 of that interaction without the benefits of prior coordination and related
  knowledge. I will conclude with some remarks on the potential practical u
 ses of such models and learning methods in a wide variety of applications 
 ranging from personal robotics to intelligent user interfaces.
LOCATION:Small public lecture room\, Microsoft Research Ltd\, 7 J J Thomso
 n Avenue (Off Madingley Road)\, Cambridge
END:VEVENT
END:VCALENDAR