# The False Dawn: Reevaluating Google's Reinforcement Learning for Chip Macro Placement

arXiv: https://arxiv.org/abs/2306.09633 · HTML: https://mlsanity.com/paper/2306.09633/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 105 references that are in the map.
- First posted on arXiv 16 Jun 2023.

## Builds on (most cited first, 3 of 3)

- [Reinforcement Learning for Combinatorial Optimization: A Survey](https://mlsanity.com/paper/2003.03600/) (2020)
- [An Updated Assessment of Reinforcement Learning for Macro Placement](https://mlsanity.com/paper/2302.11014/) (2023)
- [Delving into Macro Placement with Reinforcement Learning](https://mlsanity.com/paper/2109.02587/) (2021)

## Built on by (most cited first, 2 of 2)

- [That Chip Has Sailed: A Critique of Unfounded Skepticism Around AI for Chip Design](https://mlsanity.com/paper/2411.10053/) (2024)
- [Optimizing with Low Budgets: a Comparison on the Black-box Optimization Benchmarking Suite and OpenAI Gym](https://mlsanity.com/paper/2310.00077/) (2023)

## Abstract (arXiv)

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 drew critical media coverage. The paper withheld critical methodology steps and most inputs needed to reproduce results. Our meta-analysis shows how two separate evaluations filled in the gaps and demonstrated that Google RL lags behind (i) human designers, (ii) a well-known algorithm (Simulated Annealing), and (iii) generally-available commercial software, while being slower; and in a 2023 open research contest, RL methods weren't in top 5. Crosschecked data indicate that the integrity of the Nature paper is substantially undermined owing to errors in conduct, analysis and reporting. Before publishing, Google rebuffed internal allegations of fraud, which still stand. We note policy implications and conclusions for chip design.