BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Incorporating Domain-Specific Knowledge in Learning Control using 
 Multiple Dynamics Models - Joe Hall\, University of Cambridge
DTSTART:20131025T130000Z
DTEND:20131025T140000Z
UID:TALK47963@talks.cam.ac.uk
CONTACT:Tim Hughes
DESCRIPTION:We propose a probabilistic learning algorithm\, based on that 
 of Deisenroth & Rasmussen (2011)*\, to train control policies for nonlinea
 r systems with unknown\, or partially unknown\, dynamics. In particular\, 
 we address the issue of how to incorporate domain-specific knowledge in th
 e form of known\, or approximate\, relationships between the state variabl
 es. This covers the common case of position-velocity relationships but can
  also be used to tackle reference tracking problems. We demonstrate our ap
 proach on some learning problems including the simulated robotic unicycle.
 \n\n*Deisenroth\, M.P. & Rasmussen\, C.E. (2011) PILCO: A model-based and 
 data-efficient approach to policy search. In Proceedings of the 28th Inter
 national Conference on Machine Learning (ICML)
LOCATION: Cambridge University Engineering Department\, LR5
END:VEVENT
END:VCALENDAR