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, while taking longer to run. Crosschecked data show 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.

翻译：强化学习（RL）在芯片物理设计中的应用——谷歌2021年《自然》论文中的方法——因缺乏充分记录的主张引发争议，不仅令人质疑，还招致了批评性媒体关注。该论文隐瞒了重现其报告结果所需的大部分输入数据及方法论中的若干关键步骤。然而，两项独立评估填补了这些空白，并证明谷歌的强化学习技术落后于人类设计师、逊于众所周知的模拟退火算法，也弱于市面常见商业软件，同时运行耗时更长。交叉验证数据表明，由于研究实施、数据分析及报告撰写中的错误，该《自然》论文的完整性受到严重损害。在论文发表前，谷歌曾驳斥内部对其学术不端的指控。