Difference between revisions of "AIOP Jul. 1, 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...")
 
 
(One intermediate revision by the same user not shown)
Line 64: Line 64:
  
 
<hr>
 
<hr>
 +
 +
 +
=== Announcements ===
 +
# Torri will make slides and circulate for CAARI-SNEAP
 +
# Patrick will write and circulate abstract for PTSP2024
 +
# Jiawei will be visiting for 3 weeks (!!)
  
 
=== Minutes ===
 
=== Minutes ===
<!-- Attendees: Thomas, Torri, David, Jiawei, Naomi, Armen, Hovannes -->
+
<!-- Attendees: Torri, David, Jiawei, Armen, Hovannes, Malachi -->
 +
 
  
 +
# Review of last meeting's notes
 +
# Jiawei's slides
 +
## Used nominal coherent peak positions from wiki page Naomi sent (will try and get link)
 +
## Found cases of improper operation of the diamond, for example run 41178. Any guesses as to who was on shift ;)
 +
## Discussion on how to account for operator error and if predictions can be made about peak position based on past measurements.
 +
# Armen
 +
## Gave an initial walk through of environment implementation
 +
## Goal of environment is to get the edge to desired position by adjusting pitch and yaw. The state space consists of pitch, yaw, plane, mode, phi022, edge, req_edge, beam positions in x and y (assuming 5C11B?)
 +
## should sample historical data for initial values for reset function
 +
# Patrick
 +
## Recent Friday ML focused meetings where we discussed RL implementation using JLab DS toolkit
 +
## Developed an environment in OpenAI Gymnasium
 +
## Reviewed Ken Livingston formula
  
 
==== Action Items ====
 
==== Action Items ====
 +
<ul>
 +
<li><strong>Abstract and presentation drafts from Patrick and Torri</strong></li>
 +
<li><strong>Data prep/analysis/visualization:</strong>
 +
<ol><li>Share location of data files for use in RL and for visualization<li>
 +
<li>Add active collimator X and Y positions to datasets </li> </ol>
 +
</li>
 +
<li><strong>RL Implementation</strong>
 +
<ol><li>Review reset and reward functions and use historical data for reference values instead of random values</li>
 +
<li>Write a unit test to confirm that pitch and yaw angle changes occur in one step</li>
 +
<li>Do some sanity checking with a trivial example to verify results with known reset conditions</li>
 +
</ol>
 +
</ul>
  
 
=== Milestones! ===
 
=== Milestones! ===

Latest revision as of 12:53, 2 July 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
  3. Project Progress
  4. PIER Activities
    • Middle School Data Science Hackathon Workshop
    • HUGS mini-Workshop
  5. AOT




Announcements

  1. Torri will make slides and circulate for CAARI-SNEAP
  2. Patrick will write and circulate abstract for PTSP2024
  3. Jiawei will be visiting for 3 weeks (!!)

Minutes

  1. Review of last meeting's notes
  2. Jiawei's slides
    1. Used nominal coherent peak positions from wiki page Naomi sent (will try and get link)
    2. Found cases of improper operation of the diamond, for example run 41178. Any guesses as to who was on shift ;)
    3. Discussion on how to account for operator error and if predictions can be made about peak position based on past measurements.
  3. Armen
    1. Gave an initial walk through of environment implementation
    2. Goal of environment is to get the edge to desired position by adjusting pitch and yaw. The state space consists of pitch, yaw, plane, mode, phi022, edge, req_edge, beam positions in x and y (assuming 5C11B?)
    3. should sample historical data for initial values for reset function
  4. Patrick
    1. Recent Friday ML focused meetings where we discussed RL implementation using JLab DS toolkit
    2. Developed an environment in OpenAI Gymnasium
    3. Reviewed Ken Livingston formula

Action Items

  • Abstract and presentation drafts from Patrick and Torri
  • Data prep/analysis/visualization:
    1. Share location of data files for use in RL and for visualization
    2. Add active collimator X and Y positions to datasets
  • RL Implementation
    1. Review reset and reward functions and use historical data for reference values instead of random values
    2. Write a unit test to confirm that pitch and yaw angle changes occur in one step
    3. Do some sanity checking with a trivial example to verify results with known reset conditions

Milestones!