BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.4.5//EN
TZID:America/Los_Angeles
X-WR-TIMEZONE:America/Los_Angeles
BEGIN:VEVENT
UID:0-1872@hmc.edu
DTSTART;TZID=America/Los_Angeles:20261109T163000
DTEND;TZID=America/Los_Angeles:20261109T173000
DTSTAMP:20261106T004425Z
URL:https://www.hmc.edu/calendar/events/cs-colloquium-from-robot-learning-
 to-smart-buildings-leveraging-prior-data-and-shared-evaluation-victoria-de
 an/
SUMMARY:CS Research Talk– “From Robot Learning to Smart Buildings: Leve
 raging Prior Data and Shared Evaluation\,” Victoria Dean
DESCRIPTION:Unlike most machine learning applications\, robotics involves p
 hysical constraints that make off-the-shelf learning challenging. Difficul
 ties in large-scale data collection and training present a major roadblock
  to applying today’s data-intensive algorithms. Robot learning has an ad
 ditional roadblock in evaluation: every physical space is different\, maki
 ng results across labs inconsistent.\n\nTwo common assumptions of the robo
 t learning paradigm limit data efficiency. First\, an agent typically assu
 mes isolated environments and no prior experience. Second\, agents frequen
 tly rely on vision alone to learn tasks. Victoria Dean will present work t
 hat lifts these two assumptions\, improving the data efficiency of robot l
 earning by leveraging multimodality (images and audio) as well as pretrain
 ing. She will then introduce a real-world manipulation benchmark for evalu
 ating the generalization of policy learning methods via shared data and ha
 rdware.\n\nFinally\, Dean will turn to another robot learning application 
 at a larger scale: optimizing heating and cooling systems in our buildings
 . Buildings account for nearly 40% of carbon emissions in the U.S.\, yet m
 ost building control policies fail to generalize beyond a single building.
  She will discuss ongoing work to benchmark generalization via the Smart B
 uildings Challenge\, highlighting how machine learning can tackle pressing
  sustainability challenges.\nSpeaker\nVictoria Dean is a teaching professo
 r in the Department of Computer Science at Princeton University. Her resea
 rch interests are at the intersection of machine learning and robotics\, i
 nvestigating generalization\, benchmarking and democratization. She teache
 s across introductory computer science\, machine learning and ethics and e
 njoys implementing real-world projects in my courses. Dean is passionate a
 bout teaching and mentoring undergraduate students\, with an emphasis on i
 mproving diversity\, equity\, and inclusion.\n\nPrior to joining Princeton
 \, Dean was an assistant professor of computer science at Olin College of 
 Engineering. She did her PhD at CMU's Robotics Institute\, advised by Abhi
 nav Gupta and supported by the NSF GRFP and Siebel Scholars. She got her B
 .S. in computer science from MIT and spent time at DeepMind\, Waymo\, Deep
  Genomics\, Counsyl\, Google and Coursera.
CATEGORIES:Faculty,Staff,Students
LOCATION:Galileo Hall\, 240 Platt Blvd.\, Claremont\, CA\, 91711\, United S
 tates
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=240 Platt Blvd.\, Claremont
 \, CA\, 91711\, United States;X-APPLE-RADIUS=100;X-TITLE=Galileo Hall:geo:
 0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:STANDARD
DTSTART:20261101T010000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
END:STANDARD
END:VTIMEZONE
END:VCALENDAR