Unlocking the black box beyond Bayesian global optimization for materials design using reinforcement learning

作者：Yuehui Xian, Xiangdong Ding, Xue Jiang, Yumei Zhou, Jun Sun, Dezhen Xue, Turab Lookman · 发表于：npj Computational Materials · 年份：2025 · DOI：10.1038/s41524-025-01639-w · 被引用次数：14 · 研究领域：Topology Optimization in Engineering、Advanced Multi-Objective Optimization Algorithms、Machine Learning in Materials Science

Materials design often becomes an expensive black-box optimization problem due to limitations in balancing exploration-exploitation trade-offs in high-dimensional spaces. We propose a reinforcement learning (RL) framework that effectively navigates the complex design spaces through two complementary approaches: a model-based strategy utilizing surrogate models for sample-efficient exploration, and an on-the-fly strategy when direct experimental feedback is available. This approach demonstrates better performance in high-dimensional spaces (D ≥ 6) compared to Bayesian optimization (BO) with the Expected Improvement (EI) acquisition function through more dispersed sampling patterns and better landscape learning capabilities. Furthermore, we observe a synergistic effect when combining BO’s early-stage exploration with RL’s adaptive learning. Evaluations on both standard benchmark functions (Ackley, Rastrigin) and real-world high-entropy alloy data, demonstrate statistically significant improvements ( p < 0.01) over traditional BO with EI, particularly in complex, high-dimensional scenarios. This work addresses limitations of existing methods while providing practical tools for guiding experiments.