Soft Actor-Critic Reinforcement Learning-Based Optimization for Analog Circuit Sizing

被引：0

作者：

Park, Sejin ^{[1
]}

Choi, Youngchang ^{[1
]}

Kang, Seokhyeong ^{[1
]}

机构：

[1] POSTECH, Dep Elect Engn, Pohang, South Korea

来源：

2023 20TH INTERNATIONAL SOC DESIGN CONFERENCE, ISOCC | 2023年

基金：

新加坡国家研究基金会;

关键词：

Analog circuit optimization; Reinforcement Learning(RL); Soft actor-critic(SAC);

D O I：

10.1109/ISOCC59558.2023.10396499

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

This research proposes a Soft Actor-Critic (SAC) based RL approach to optimize analog circuit sizing. The SAC algorithm efficiently addresses challenges in continuous state and action spaces, providing stable learning and sample efficiency. Comparative experiments were conducted on a 2-stage OTA and a 3-stage TIA, showing that SAC outperforms DDPG and TD3 in terms of success rate, average FoM, and minimum power consumption. The results demonstrate the effectiveness of the proposed SAC-based RL architecture for analog circuit optimization.

引用

页码：47 / 48

页数：2

共 6 条

[1] DNN-Opt: An RL Inspired Optimization for Analog Circuit Sizing using Deep Neural Networks [J].

Budak, Ahmet F. ;

Bhansali, Prateek ;

Liu, Bo ;

Sun, Nan ;

Pan, David Z. ;

Kashyap, Chandramouli, V .

2021 58TH ACM/IEEE DESIGN AUTOMATION CONFERENCE (DAC), 2021, :1219-1224

[2]

Fujimoto S, 2018, PR MACH LEARN RES, V80

[3]

Haarnoja T, 2018, PR MACH LEARN RES, V80

[4]

Lillicrap T. P., 2015, arXiv, DOI DOI 10.48550/ARXIV.1509.02971

[5]

Settaluri K, 2020, DES AUT TEST EUROPE, P490, DOI 10.23919/DATE48585.2020.9116200

[6] GCN-RL Circuit Designer: Transferable Transistor Sizing with Graph Neural Networks and Reinforcement Learning [J].

Wang, Hanrui ;

Wang, Kuan ;

Yang, Jiacheng ;

Shen, Linxiao ;

Sun, Nan ;

Lee, Hae-Seung ;

Han, Song .

PROCEEDINGS OF THE 2020 57TH ACM/EDAC/IEEE DESIGN AUTOMATION CONFERENCE (DAC), 2020,

← 1 →