强化学习
计算机科学
机器学习
人工智能
匹配(统计)
理论(学习稳定性)
可靠性(半导体)
功能(生物学)
领域(数学分析)
钥匙(锁)
趋同(经济学)
财产(哲学)
主动学习(机器学习)
重要性抽样
采样(信号处理)
限制
数据挖掘
空格(标点符号)
自举(财务)
期限(时间)
面子(社会学概念)
领域知识
反向
实验数据
结构化预测
主题专家
资源(消歧)
对比度(视觉)
边距(机器学习)
作者
Yeyong Yu,Xilei Bian,Jie Xiong,Xudong Wu,Quan QIAN
标识
DOI:10.1038/s41524-025-01894-x
摘要
With the growing demand for novel materials, machine learning-driven inverse design methods face significant challenges in reconciling the high-dimensional materials composition space with limited experimental data. Existing approaches suffer from two major limitations: (I) machine learning models often lack reliability in high-dimensional spaces, leading to prediction biases during the design process; (II) these models fail to effectively incorporate domain expert knowledge, limiting their capacity to support knowledge-guided inverse design. To address these challenges, we present AIMATDESIGN, a reinforcement learning framework that augments experimental data via difference-based sampling to build a trusted experience pool. To enhance model reliability, an automated refinement strategy guided by large language models corrects prediction inconsistencies, ensuring better alignment between reward signals and value functions. Additionally, a knowledge-based reward further leverages expert rules to improve stability and efficiency. Experiments show that AIMATDESIGN outperforms conventional machine learning and reinforcement learning baselines in discovery efficiency, convergence speed, and success rates. From numerous candidates, experimental validation of Zr-based alloys yielded a bulk metallic glass with 1.7 GPa yield strength and 10.2% elongation, closely matching predictions. This framework demonstrates reliable performance in capturing property trends and provides a general pathway toward closed-loop, data-efficient materials discovery.
科研通智能强力驱动
Strongly Powered by AbleSci AI