BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260402T024534Z
LOCATION:Level 2 Lobby
DTSTART;TZID=America/Los_Angeles:20250623T180000
DTEND;TZID=America/Los_Angeles:20250623T190000
UID:dac_DAC 2025_sess287_LBR101@linklings.com
SUMMARY:Late Breaking Results: Breaking Symmetry--- Unconventional Placeme
 nt of Analog Circuits using Multi-Level Multi-Agent Reinforcement Learning
DESCRIPTION:Supriyo Maji, Linran Zhao, Souradip Poddar, and David Pan (The
  University of Texas at Austin)\n\nLayout-dependent effects (LDEs) signifi
 cantly impact analog circuit performance. Traditionally, designers have re
 lied on symmetric placement of circuit components to mitigate variations c
 aused by LDEs. However, due to non-linear nature of these effects, convent
 ional methods often fall short. We propose an objective-driven, multi-leve
 l, multi-agent Q-learning framework to explore unconventional design space
  of analog layout, opening new avenues for optimizing analog circuit perfo
 rmance. Our approach achieves better variation performance than the state-
 of-the-art layout techniques. Notably, this is the first application of mu
 lti-agent RL in analog layout automation. The proposed approach is compare
 d with non-ML approach based on simulated annealing.\n\n
END:VEVENT
END:VCALENDAR