arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.02308cs.LGcs.AIphysics.chem-ph
收藏

AdsorbRL:面向催化剂逆向设计的深度多目标强化学习

AdsorbRL: Deep Multi-Objective Reinforcement Learning for Inverse Catalysts Design

Stanford University(斯坦福大学)

Romain Lacombe, Lucas Hendren, Khalid El-Awady

AI总结:

本文提出深度强化学习智能体 AdsorbRL,用于在约16万种化合物空间中逆向设计催化剂;通过随机边遍历和目标子采样等方法,在单目标与多目标结合能优化上分别平均提升4.1 eV和0.8 eV。

摘要:

清洁能源转型的一项核心挑战是开发低排放技术所需的催化剂。机器学习在量子化学中的最新进展显著加速了对吸附能等催化活性描述符的计算。本文提出 AdsorbRL,这是一个深度强化学习智能体,旨在在给定多目标结合能目标的情况下识别潜在催化剂;它利用 Open Catalyst 2020 和 Materials Project 数据集,通过离线学习进行训练。我们实验了 Deep Q-Network 智能体,以遍历由 55 种化学元素构成的约 160,000 种可能的一元、二元和三元化合物的全部空间;奖励极为稀疏,因为对于每种吸附物,仅有 2,000 至 3,000 种催化剂的吸附能是已知的。为约束动作空间,我们提出 Random Edge Traversal,并在已知状态子图上训练一个单目标 DQN 智能体;结果发现,该方法平均使目标结合能增强 4.1 eV。我们将此方法扩展到多目标、目标条件化学习,并训练一个 DQN 智能体,以针对多个同时存在的目标吸附物识别具有最高(相应地,最低)吸附能的材料。我们实验了 Objective Sub-Sampling,这是一种旨在鼓励多目标设置中探索的新型训练方案,并证明所有目标吸附物的吸附能均得到同步改善,平均提升 0.8 eV。总体而言,我们的结果表明,深度强化学习在催化剂逆向设计问题中具有强大潜力。

英文摘要:

A central challenge of the clean energy transition is the development of catalysts for low-emissions technologies. Recent advances in Machine Learning for quantum chemistry drastically accelerate the computation of catalytic activity descriptors such as adsorption energies. Here we introduce AdsorbRL, a Deep Reinforcement Learning agent aiming to identify potential catalysts given a multi-objective binding energy target, trained using offline learning on the Open Catalyst 2020 and Materials Project data sets. We experiment with Deep Q-Network agents to traverse the space of all ~160,000 possible unary, binary and ternary compounds of 55 chemical elements, with very sparse rewards based on adsorption energy known for only between 2,000 and 3,000 catalysts per adsorbate. To constrain the actions space, we introduce Random Edge Traversal and train a single-objective DQN agent on the known states subgraph, which we find strengthens target binding energy by an average of 4.1 eV. We extend this approach to multi-objective, goal-conditioned learning, and train a DQN agent to identify materials with the highest (respectively lowest) adsorption energies for multiple simultaneous target adsorbates. We experiment with Objective Sub-Sampling, a novel training scheme aimed at encouraging exploration in the multi-objective setup, and demonstrate simultaneous adsorption energy improvement across all target adsorbates, by an average of 0.8 eV. Overall, our results suggest strong potential for Deep Reinforcement Learning applied to the inverse catalysts design problem.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑