Adaptive Transient Stepping Policy on Reinforcement Learning
2023 International Symposium of Electronics Design Automation (ISEDA)(2023)
摘要
Transient analysis (TA) is the foundation for nonlinear electronic circuit simulation, which determines the time-domain response of the circuit over a specified time interval. However, it is usually computationally intensive and quite time-consuming without careful parameter tuning and proper stepping policy. In this paper, reinforcement learning (RL) is introduced to design a effective transient stepping policy (TSP). The online RL-based TSP works with bidirectional agents and state-switch samples, enabling our model to adaptively and intelligently adjust the bidirectional step sizes in TA. The proposed RL-based TSP has been implemented in an open source SPICE-like simulator, and has achieved remarkable simulation efficiency speedup while maintaining reasonable simulation accuracy.
更多查看译文
关键词
Transient analysis,stepping policy,LTE,rein-forcement learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要