[Colloquium] 11/19 TTIC Colloquium: Scott Niekum, University of Texas at Austin

Mary Marre via Colloquium colloquium at mailman.cs.uchicago.edu
Mon Nov 12 18:13:14 CST 2018


*When:    *  Monday, November 19th at 11:00 am



*Where:     *TTIC, 6045 S. Kenwood Avenue, 5th Floor, Room 526



*Who:        *Scott Niekum, University of Texas at Austin



*Title:        *Scaling Probabilistically Safe Learning to Robotics

*Abstract:*
Before learning robots can be deployed in the real world, it is critical
that probabilistic guarantees can be made about the safety and performance
of such systems.  In recent years, so-called “safe-learning” algorithms
have enjoyed success in application areas with high-quality models and
plentiful data, but robotics remains a challenging domain for scaling up
such approaches. Notably, current methods typically fail to meet at least
one of the three following criteria: (1) providing probabilistic, rather
than heuristic-based performance guarantees, (2) not relying on perfect or
near-perfect models that are unobtainable in practice, and (3) being
sufficiently sample efficient to work with robot-sized amounts of data.  In
this talk, we challenge several common, but incorrect, assumptions about
reinforcement and imitation learning, resulting in novel safe learning
algorithms that exhibit state-of-the-art data efficiency and performance.
These algorithms offer a blend of safety and practicality that serves as a
significant step towards high-confidence robot learning with modest amounts
of real-world data.

*Bio:*
Scott Niekum is an Assistant Professor and the director of the Personal
Autonomous Robotics Lab (PeARL) in the Department of Computer Science at UT
Austin.  He is also a core faculty member in the interdepartmental robotics
group at UT.  Prior to joining UT Austin, Scott was a postdoctoral research
fellow at the Carnegie Mellon Robotics Institute and received his Ph.D.
from the Department of Computer Science at the University of Massachusetts
Amherst.  His research interests include imitation learning, reinforcement
learning, and robotic manipulation. Scott is a recipient of the 2018 NSF
CAREER Award.

*Host:* Matthew Walter <mwalter at ttic.edu>


For more information on the colloquium series or to subscribe to the
mailing list,please see http://www.ttic.edu/colloquium.php


Mary C. Marre
Administrative Assistant
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Room 517*
*Chicago, IL  60637*
*p:(773) 834-1757*
*f: (773) 357-6970*
*mmarre at ttic.edu <mmarre at ttic.edu>*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20181112/2a2b0eb3/attachment.html>


More information about the Colloquium mailing list