Volltext-Downloads (blau) und Frontdoor-Views (grau)
The search result changed since you submitted your search request. Documents might be displayed in a different sort order.
  • search hit 1 of 48
Back to Result List

Deep reinforcement learning for analog circuit sizing with an electrical design space and sparse rewards

  • There is still a great reliance on human expert knowledge during the analog integrated circuit sizing design phase due to its complexity and scale, with the result that there is a very low level of automation associated with it. Current research shows that reinforcement learning is a promising approach for addressing this issue. Similarly, it has been shown that the convergence of conventional optimization approaches can be improved by transforming the design space from the geometrical domain into the electrical domain. Here, this design space transformation is employed as an alternative action space for deep reinforcement learning agents. The presented approach is based entirely on reinforcement learning, whereby agents are trained in the craft of analog circuit sizing without explicit expert guidance. After training and evaluating agents on circuits of varying complexity, their behavior when confronted with a different technology, is examined, showing the applicability, feasibility as well as transferability of this approach.

Download full text files

  • 3804.pdf
    eng

Export metadata

Additional Services

Search Google Scholar

Statistics

frontdoor_oas
Metadaten
Author of HS ReutlingenUhlmann, Yannick; Scheible, Jürgen; Curio, Cristóbal; Bramlage, Lennart; Essich, Michael
DOI:https://doi.org/10.1145/3551901.3556474
ISBN:978-1-4503-9486-4
Erschienen in:MLCAD '22: Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD, 12-13 September 2022, Snowbird, USA
Publisher:ACM
Place of publication:New York
Document Type:Conference proceeding
Language:English
Publication year:2022
Tag:analog circuit sizing; neural networks; reinforcement learning
Page Number:6
First Page:21
Last Page:26
DDC classes:600 Technik
Open access?:Nein
Licence (German):License Logo  In Copyright - Urheberrechtlich geschützt