Reinforcement Learning for Routing

Haiguang Liao () and Levent Burak Kara ()
Additional contact information
Haiguang Liao: Carnegie Mellon University
Levent Burak Kara: Carnegie Mellon University

Chapter Chapter 11 in Machine Learning Applications in Electronic Design Automation, 2022, pp 277-306 from Springer

Abstract: Abstract Routing has been one of the most critical and challenging steps in electronics design automation (EDA), and existing solutions have historically relied heavily on heuristics and analytical methods. In recent years, reinforcement learning (RL) has emerged as an alternative for use in various routing problems in the space of chip design. RL-based methods tend to outperform existing heuristics and analytical routing algorithms across various metrics including efficiency and solution quality, and a few are able to solve problems that previously remained unsolved. This chapter provides a review of recent RL routing approaches in EDA and shares insights into open challenges and opportunities. Methods covered in this chapter include RL for global routing, RL for detailed routing, RL for standard cell routing, and RL for other related routing problems.

Keywords: Reinforcement learning; Routing; Net ordering; Standard cell routing; Steiner tree (search for similar items in EconPapers)
Date: 2022
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-031-13074-8_11

Ordering information: This item can be ordered from
http://www.springer.com/9783031130748

DOI: 10.1007/978-3-031-13074-8_11

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().