BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Supervising Robot Learning with Language and Video from the Web - 
 Suraj Nair\, Stanford University
DTSTART:20211118T150000Z
DTEND:20211118T160000Z
UID:TALK165949@talks.cam.ac.uk
CONTACT:Marinela Parovic
DESCRIPTION:While deep reinforcement learning applied to robotics has seen
  a number of recent successes in constrained environments\, generalist rob
 ots that can operate in diverse real world settings have remained out of r
 each. Critically\, robot learning algorithms have yet to be able to learn 
 from a sufficient breadth of data that can enable broad generalization acr
 oss tasks and environments. In this talk\, I’ll discuss the paradigm of 
 offline learning for robotics as a path towards generalist robots\, and ho
 w we might supervise this offline learning process in a scalable way using
  crowdsourced language and videos of humans. Specifically\, I’ll cover t
 wo recent papers which learn reward functions for offline reinforcement le
 arning through language annotations of pre-collected robot datasets and hu
 man video datasets which exist on the web.
LOCATION:https://cam-ac-uk.zoom.us/j/97599459216?pwd=QTRsOWZCOXRTREVnbTJBd
 XVpOXFvdz09
END:VEVENT
END:VCALENDAR