BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20211207T055414Z
LOCATION:Online
DTSTART;TZID=America/Chicago:20211119T111000
DTEND;TZID=America/Chicago:20211119T113000
UID:submissions.supercomputing.org_SC21_sess338_ws_xloop106@linklings.com
SUMMARY:Optimizing High-Throughput Capabilities by Leveraging Reinforcemen
 t Learning Methods with the Bluesky Suite
DESCRIPTION:Workshop\n\nOptimizing High-Throughput Capabilities by Leverag
 ing Reinforcement Learning Methods with the Bluesky Suite\n\nOlds, Allan, 
 Caswell, Lynch, Maffettone...\n\nModern light sources have dramatically in
 creased available photon flux at beamlines, allowing greatly increased mea
 surement speeds for many techniques and enabling high-throughput modes.  T
 he limiting factor in optimizing such processes is typically driven by var
 iations in sample composition leading to differing requirements for measur
 ement time to achieve optimal measurement statistics across all samples.  
 When human-driven, such dynamic sample-by-sample scheduling operations are
  at best tedious and at worst unoptimized or mistake prone.  Reinforcement
  learning methods offer a path to autonomously drive such high-throughput 
 experiments, and the Bluesky suite allows for their ready integration.  In
  this contribution we will discuss how reinforcement learning aids high-th
 roughput data collection and practical considerations for implementing the
 se methods on a beamline.\n\nTag: Online Only, Applications, Scientific Co
 mputing\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR