BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20241120T082409Z
LOCATION:HG E 3
DTSTART;TZID=Europe/Stockholm:20240604T113000
DTEND;TZID=Europe/Stockholm:20240604T120000
UID:submissions.pasc-conference.org_PASC24_sess144_msa199@linklings.com
SUMMARY:Relexi: Reinforcement Learning for Applications in Computational F
 luid Dynamics
DESCRIPTION:Minisymposium\n\nMarius Kurz (University of Stuttgart), Philip
 p Offenhäuser (HPE), Benjamin Sanderse (Centrum Wiskunde & Informatica (CW
 I)), and Andrea Beck (University of Stuttgart)\n\nRelexi is a powerful too
 l that allows to use existing simulation codes as training environments fo
 r reinforcement learning (RL) on high-performance computing (HPC) systems.
  This framework allows to apply RL to problems typically requiring HPC har
 dware such as computational fluid dynamics (CFD) or related fields. For th
 is, Relexi applies the SmartSim library, which allows to manage the indivi
 dual simulation environments on HPC systems and provides an efficient comm
 unication channel between itself and the simulation code. In this talk, we
  demonstrate two specific applications for the use of RL in CFD. First, we
  apply the framework to a task in active flow control. Here, the RL agent 
 is trained to minimize the drag for the flow around a two-dimensional cyli
 nder using blowing and suction jets at the cylinder’s poles. For this case
 , the agent is demonstrated to reduce the experienced drag by about 15%. M
 oreover, Relexi is applied to the task of turbulence modeling in large edd
 y simulation, where it was found to outperform traditional models, while b
 eing robust against changes in resolution, Reynolds number, and also when 
 applied to heavily deformed meshes.\n\nDomain: Chemistry and Materials, Cl
 imate, Weather, and Earth Sciences, Engineering, Computational Methods and
  Applied Mathematics\n\nSession Chair: Riccardo Balin (Argonne National La
 boratory)
END:VEVENT
END:VCALENDAR