[2306.09633] The False Dawn: Reevaluating Google's Reinforcement Learning for Ch...
source link: https://arxiv.org/abs/2306.09633
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
[Submitted on 16 Jun 2023 (v1), last revised 21 Jun 2023 (this version, v3)]
The False Dawn: Reevaluating Google's Reinforcement Learning for Chip Macro Placement
Reinforcement learning (RL) for physical design of silicon chips in a Google 2021 Nature paper stirred controversy due to poorly documented claims that raised eyebrows and attracted critical media coverage. The Nature paper withheld most inputs needed to produce reported results and some critical steps in the methodology. But two separate evaluations filled in the gaps and demonstrated that Google RL lags behind human designers, behind a well-known algorithm (Simulated Annealing), and also behind generally-available commercial software. Crosschecked data indicate that the integrity of the Nature paper is substantially undermined owing to errors in the conduct, analysis and reporting.
Comments: | 14 pages, 1 figure, 3 tables (v3 clarifies the numbers of chip design examples used in [1]) |
Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Hardware Architecture (cs.AR); Computers and Society (cs.CY) |
Cite as: | arXiv:2306.09633 [cs.LG] |
(or arXiv:2306.09633v3 [cs.LG] for this version) | |
https://doi.org/10.48550/arXiv.2306.09633
arXiv-issued DOI via DataCite
|
Recommend
About Joyk
Aggregate valuable and interesting links.
Joyk means Joy of geeK