Difference between revisions of "AIOP Aug. 26, 2024"

From epsciwiki
Jump to navigation Jump to search
(Created page with "The current weekly meeting time is every other Monday at 13:00 US/Eastern === Connection Info: === <div class="toccolours mw-collapsible mw-collapsed"> You can connect using...")
 
 
Line 75: Line 75:
 
=== Minutes ===
 
=== Minutes ===
 
<!-- Attendees: Torri, David, Jiawei, Armen, Hovannes, Malachi -->
 
<!-- Attendees: Torri, David, Jiawei, Armen, Hovannes, Malachi -->
 +
<h2>Attendees</h2>
 +
<ul>
 +
  <li>Thomas</li>
 +
  <li>David</li>
 +
  <li>Torri</li>
 +
  <li>Naomi</li>
 +
  <li>Armen</li>
 +
  <li>Malachi</li>
 +
  <li>Cristiano</li>
 +
</ul>
  
 +
<h3>More Discussions of Button Pressing</h3>
 +
<ul>
 +
  <li>Does it actually solve the differential problem?
 +
    <ul>
 +
      <li>Conditionals</li>
 +
    </ul>
 +
  </li>
 +
  <li>Some arguments on whether to train to buttons or goni angles and whether conditionals are needed</li>
 +
  <li>Thomas: What is our model’s output?</li>
 +
  <li>David: We’ll need to prove it</li>
 +
  <li>Agreed to do the easy thing first (single mode)
 +
    <ul>
 +
      <li>Malachi pointed out that the framework for the conditionals already exists</li>
 +
    </ul>
 +
  </li>
 +
</ul>
  
 +
<h3>Progress</h3>
 +
 +
<ul>
 +
  <li><strong>Patrick</strong>
 +
    <ul>
 +
      <li>Showed tensor board on the current state of RL
 +
        <ul>
 +
          <li>Some bug fixes</li>
 +
          <li>Armen: Ironing out the action space</li>
 +
        </ul>
 +
      </li>
 +
    </ul>
 +
  </li>
 +
 
 +
  <li><strong>Jaiwei</strong>
 +
    <ul>
 +
      <li>Working on training pitch, yaw, beamx, beamy to coherent edge position from a single mode with Armen</li>
 +
      <li>Jaiwei normalized… need to transform them back</li>
 +
      <li>Showing some promise</li>
 +
    </ul>
 +
  </li>
 +
 +
  <li><strong>Patrick</strong>
 +
    <ul>
 +
      <li>Showed MeV residuals
 +
        <ul>
 +
          <li>~20 MeV with outliers of 100 MeV</li>
 +
          <li>Cristiano: Plotted errors would be good</li>
 +
        </ul>
 +
      </li>
 +
    </ul>
 +
  </li>
 +
</ul>
  
 
=== Milestones! ===
 
=== Milestones! ===

Latest revision as of 16:07, 9 September 2024

The current weekly meeting time is every other Monday at 13:00 US/Eastern

Connection Info:

You can connect using ZOOM Video conferencing (ID: 161 588 8669). (Click "Expand" to the right for details -->):

One tap mobile: US: +16692545252,,1602484178# or +16468287666,,1602484178#

Meeting URL: https://jlab-org.zoomgov.com/j/1615888669?pwd=MnhGVUhpeEd3NVpnTGxoZHJManNBdz09&from=addon
Meeting ID: 161 588 8669
Passcode: 561441

Join by Telephone
For higher quality, dial a number based on your current location.
Dial: +1 669 254 5252 US (San Jose)
+1 646 828 7666 US (New York)
+1 646 964 1167 US (US Spanish Line)
+1 551 285 1373 US (New Jersey)
+1 669 216 1590 US (San Jose)
+1 415 449 4000 US (US Spanish Line)
833 568 8864 US Toll-free
Meeting ID: 161 588 8669
International numbers
Join from an H.323/SIP room system
H.323: 161.199.138.10 (US West)
161.199.136.10 (US East)
Meeting ID: 161 588 8669
Passcode: 561441

SIP: 1615888669@sip.zoomgov.com
Passcode: 561441

One tap mobile: US: +16692545252,,1601987443# or +16468287666,,1601987443#

Meeting URL: https://jlab-org.zoomgov.com/j/1615888669?pwd=MnhGVUhpeEd3NVpnTGxoZHJManNBdz09&from=addon
Meeting ID: 161 588 8669
Passcode: 561441

AIOP - Polarized Photon Source

Agenda:

  1. Previous Meeting
  2. Announcements
    • Quarterly sent to DOE
  3. Conferences/Workshops
    • CHEP2024 (Oct. 19-25, Krakow, Poland)Oral presentation accepted (Torri)
  4. Project Progress
  5. PIER Activities
    • Middle School Data Science Hackathon Workshop
    • HUGS mini-Workshop - COMPLETED!
  6. AOT



Minutes

Attendees

  • Thomas
  • David
  • Torri
  • Naomi
  • Armen
  • Malachi
  • Cristiano

More Discussions of Button Pressing

  • Does it actually solve the differential problem?
    • Conditionals
  • Some arguments on whether to train to buttons or goni angles and whether conditionals are needed
  • Thomas: What is our model’s output?
  • David: We’ll need to prove it
  • Agreed to do the easy thing first (single mode)
    • Malachi pointed out that the framework for the conditionals already exists

Progress

  • Patrick
    • Showed tensor board on the current state of RL
      • Some bug fixes
      • Armen: Ironing out the action space
  • Jaiwei
    • Working on training pitch, yaw, beamx, beamy to coherent edge position from a single mode with Armen
    • Jaiwei normalized… need to transform them back
    • Showing some promise
  • Patrick
    • Showed MeV residuals
      • ~20 MeV with outliers of 100 MeV
      • Cristiano: Plotted errors would be good

Milestones!

Retrieved from "https://wiki.jlab.org/epsciwiki/index.php?title=AIOP_Aug._26,_2024&oldid=5426"