微信内可能无法直接打开本站。请点右上角 ··· → 在浏览器打开，或复制链接。
Reinforcement learning steers generative crystal design
RSS 官方收录 · 可信分层展示
关键摘要
强化学习引导生成式AI设计新型功能晶体材料
- 生成式机器学习在晶体发现中存在探索局限
- 新方法用强化学习定向生成新颖有用材料
- 研究发表于2026年8月《Nature Machine Intelligence》
AI 摘要 · 来源可核验
正文提要
Nature Machine Intelligence, Published online: 03 August 2026; doi:10.1038/s42256-026-01282-0
Generative machine learning methods have led to progress in crystal discovery, but cannot fully explore the space of material candidates that are both novel and useful. A reinforcement learning-based method steers candidate generation to these areas, enabling the design of novel functional materials.