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:20240626T180034Z
LOCATION:3002\, 3rd Floor
DTSTART;TZID=America/Los_Angeles:20240627T110000
DTEND;TZID=America/Los_Angeles:20240627T111500
UID:dac_DAC 2024_sess160_RESEARCH1630@linklings.com
SUMMARY:Using Probabilistic Model Rollouts to Boost the Sample Efficiency 
 of Reinforcement Learning for Automated Analog Circuit Sizing
DESCRIPTION:Research Manuscript\n\nMohsen Ahmadzadeh and Georges Gielen (K
 U Leuven)\n\nDespite recent advances in algorithms such as the use of rein
 forcement learning, analog circuit sizing optimization remains a challengi
 ng task that demands numerous circuit simulations, hence extensive CPU tim
 es. This paper presents the application of Model-Based Policy Optimization
  (MBPO) to boost the sample efficiency of reinforcement learning for analo
 g circuit sizing. This method leverages an ensemble of probabilistic dynam
 ic models to generate short rollouts branched from real data for a fast ex
 tensive exploration of the design space, thereby speeding up the learning 
 process of the reinforcement learning agent and enhancing its convergence.
  Integrated in the Twin Delayed DDPG (TD3) algorithm, our new model-based 
 TD3 (MBTD3) approach has been validated on analog circuits of different co
 mplexity, outperforming the existing model-free TD3 method by achieving po
 wer/area-optimal design solutions with up to 3x fewer simulations and half
  the run time. In addition, for larger analog circuits, we present a multi
 -agent version of MBTD3 in which multiple simultaneous agents use global p
 robabilistic models for sizing different blocks within the circuit. Demons
 trated for a complex data receiver circuit, it surpasses the model-free mu
 lti-agent TD3 method at 2x less simulations and half the run time. These n
 ovel methods highly boost the efficiency of automated analog circuit sizin
 g.\n\nTopic: EDA\n\nKeyword: Analog CAD, Simulation, Verification and Test
 \n\nSession Chair: Markus Olbrich (Leibniz University Hannover)
END:VEVENT
END:VCALENDAR