A Reinforcement Learning-Based Framework for Solving Physical Design Routing Problem in the Absence of Large Test Sets

Advances in Electronic Design Automation(EDA) methods have made the designers and programmers to search for new ways to solve the complex problems seen in today’s Very Large Scale Integration circuits. Machine learning (ML), especially supervised learning, has been used to predict design rule violations. However, supervised learning requires large amount of labeled data. With the competitive nature of EDA based companies, there is limited access to benchmarks and labeled data. In this work, we propose a data-independent reinforcement learning (RL) based routing model called Alpha-PD-Router, which learns to route a circuit and correct short violations. The Alpha-PD-Router is based on a two-player collaborative game model that has been trained on a small circuit and successfully resolves 75 violations in 99 cases of 2 pins net arrangements in the testing phase. The proposed model has the potential to be used as a framework to develop RL based routing techniques untethered by the scarce availability of large routing data samples or designer expertise. Index Terms—Physical design, routing, machine learning, reinforcement learning, collaborative min-max game theory