請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/89490完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 李奕霈 | zh_TW |
| dc.contributor.advisor | Yi-Pei Li | en |
| dc.contributor.author | 張育誠 | zh_TW |
| dc.contributor.author | Yu-Cheng Chang | en |
| dc.date.accessioned | 2023-09-07T17:14:03Z | - |
| dc.date.available | 2025-12-31 | - |
| dc.date.copyright | 2023-09-11 | - |
| dc.date.issued | 2023 | - |
| dc.date.submitted | 2023-08-01 | - |
| dc.identifier.citation | Bell, A. T.; Head-Gordon, M. Quantum Mechanical Modeling of Catalytic Processes. Annu. Rev. Chem. Biomol. Eng. 2011, 2 (1), 453–477. https://doi.org/10.1146/annurev-chembioeng-061010-114108.
Yeh, J.-Y.; Li, S.-C.; Chen, C. H.; Wu, K. C.-W.; Li, Y.-P. Quantum Mechanical Calculations for Biomass Valorization over Metal-Organic Frameworks (MOFs). Chem. – Asian J. 2021, 16 (9), 1049–1056. https://doi.org/10.1002/asia.202001371. Li, S.-C.; Lin, Y.-C.; Li, Y.-P. Understanding the Catalytic Activity of Microporous and Mesoporous Zeolites in Cracking by Experiments and Simulations. Catalysts 2021, 11 (9), 1114. https://doi.org/10.3390/catal11091114. Gong, Z.-J.; Narayana, Y. S. L. V.; Lin, Y.-C.; Huang, W.-H.; Su, W.-N.; Li, Y.-P.; Higuchi, M.; Yu, W.-Y. Rational Synthesis of Ruthenium-Based Metallo-Supramolecular Polymers as Heterogeneous Catalysts for Catalytic Transfer Hydrogenation of Carbonyl Compounds. Appl. Catal. B Environ. 2022, 312, 121383. https://doi.org/10.1016/j.apcatb.2022.121383. Ho, W. H.; Li, S.-C.; Wang, Y.-C.; Chang, T.-E.; Chiang, Y.-T.; Li, Y.-P.; Kung, C.-W. Proton-Conductive Cerium-Based Metal–Organic Frameworks. ACS Appl. Mater. Interfaces 2021, 13 (46), 55358–55366. https://doi.org/10.1021/acsami.1c17396. Schlegel, H. B. Exploring Potential Energy Surfaces for Chemical Reactions: An Overview of Some Practical Methods. J. Comput. Chem. 2003, 24 (12), 1514–1527. https://doi.org/10.1002/jcc.10231. Schlegel, H. B. Advanced Chemical Physics; John Wiley & Sons, 2007. Cramer, C. J. Essentials of Computational Chemistry: Theories and Models; John Wiley & Sons, 2013. Hratchian, H. P.; Schlegel, H. B. In Theory and Applications of Computational Chemistry; Dykstra, C. E., Frenking, G., Kim, K. S., Scuseria, G. E., Eds.; Elsevier: Amsterdam, 2005; pp 195–249. https://doi.org/10.1016/B978-044451719-7/50053-6. Jensen, F. Introduction to Computational Chemistry; John wiley & sons, 2017. Liotard, D. A. Algorithmic Tools in the Study of Semiempirical Potential Surfaces. Int. J. Quantum Chem. 1992, 44 (5), 723–741. https://doi.org/10.1002/qua.560440505. Schlegel, H. B. Geometry Optimization. WIREs Comput. Mol. Sci. 2011, 1 (5), 790–809. https://doi.org/10.1002/wcms.34. Schlegel, H. B. Geometry Optimization on Potential Energy Surfaces. In Modern Electronic Structure Theory; Advanced Series in Physical Chemistry; World Scientific Publishing Company, 1995; pp 459–500. https://doi.org/10.1142/9789812832108_0008. Gill, P. E. Practical Optimization; Emerald Group Publishing Limited, 1982. Head, J. D.; Weiner, B.; Zerner, M. C. A Survey of Optimization Procedures for Stable Structures and Transition States. Int. J. Quantum Chem. 1988, 33 (3), 177–186. https://doi.org/10.1002/qua.560330303. Bitzek, E.; Koskinen, P.; Gähler, F.; Moseler, M.; Gumbsch, P. Structural Relaxation Made Simple. Phys. Rev. Lett. 2006, 97 (17), 170201. https://doi.org/10.1103/PhysRevLett.97.170201. Farkas, Ö.; Schlegel, H. B. Methods for Optimizing Large Molecules. Part III. An Improved Algorithm for Geometry Optimization Using Direct Inversion in the Iterative Subspace (GDIIS). Phys. Chem. Chem. Phys. 2002, 4 (1), 11–15. https://doi.org/10.1039/B108658H. CAUCHY, A. Methode Generale Pour La Resolution Des Systemes d’equations Simultanees. CR Acad Sci Paris 1847, 25, 536–538. Hestenes, M. R.; Stiefel, E. Methods of Conjugate Gradients for Solving Linear Systems. 28. Broyden, C. G. The Convergence of a Class of Double-Rank Minimization Algorithms 1. General Considerations. IMA J. Appl. Math. 1970, 6 (1), 76–90. Shanno, D. F. Conditioning of Quasi-Newton Methods for Function Minimization. Math. Comput. 1970, 24 (111), 647–656. Goldfarb, D. A Family of Variable-Metric Methods Derived by Variational Means. Math. Comput. 1970, 24 (109), 23. Fletcher, R. A New Approach to Variable Metric Algorithms. Comput. J. 1970, 13 (3), 317–322. Murtagh, B. A.; Sargent, R. W. Computational Experience with Quadratically Convergent Minimisation Methods. Comput. J. 1970, 13 (2), 185–194. Moré, J. J.; Thuente, D. J. Line Search Algorithms with Guaranteed Sufficient Decrease. ACM Trans. Math. Softw. 1994, 20 (3), 286–307. https://doi.org/10.1145/192115.192132. Császár, P.; Pulay, P. Geometry Optimization by Direct Inversion in the Iterative Subspace. J. Mol. Struct. 1984, 114, 31–34. https://doi.org/10.1016/S0022-2860(84)87198-7. Levenberg, K. A Method for the Solution of Certain Non-Linear Problems in Least Squares. Q. Appl. Math. 1944, 2 (2), 164–168. https://doi.org/10.1090/qam/10666. Nesterov, Y.; Polyak, B. T. Cubic Regularization of Newton Method and Its Global Performance. Math. Program. 2006, 108 (1), 177–205. https://doi.org/10.1007/s10107-006-0706-8. Andrychowicz, M.; Denil, M.; Gómez, S.; Hoffman, M. W.; Pfau, D.; Schaul, T.; Shillingford, B.; de Freitas, N. Learning to Learn by Gradient Descent by Gradient Descent. Adv. Neural Inf. Process. Syst. 2016, 29, 3981–3989. Li, K.; Malik, J. Learning to Optimize. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings; 2017. Fawzi, A.; Balog, M.; Huang, A.; Hubert, T.; Romera-Paredes, B.; Barekatain, M.; Novikov, A.; R. Ruiz, F. J.; Schrittwieser, J.; Swirszcz, G.; Silver, D.; Hassabis, D.; Kohli, P. Discovering Faster Matrix Multiplication Algorithms with Reinforcement Learning. Nature 2022, 610 (7930), 47–53. https://doi.org/10.1038/s41586-022-05172-4. Ahuja, K.; Green, W. H.; Li, Y.-P. Learning to Optimize Molecular Geometries Using Reinforcement Learning. J. Chem. Theory Comput. 2021, 17 (2), 818–825. https://doi.org/10.1021/acs.jctc.0c00971. Halgren, T. A. Merck Molecular Force Field. I. Basis, Form, Scope, Parameterization, and Performance of MMFF94. J. Comput. Chem. 1996, 17 (5–6), 490–519. https://doi.org/10.1002/(SICI)1096-987X(199604)17:5/6<490::AID-JCC1>3.0.CO;2-P. Halgren, T. A. Merck Molecular Force Field. II. MMFF94 van Der Waals and Electrostatic Parameters for Intermolecular Interactions. J. Comput. Chem. 1996, 17 (5‐6), 520–552. Halgren, T. A. Merck Molecular Force Field. III. Molecular Geometries and Vibrational Frequencies for MMFF94. J. Comput. Chem. 1996, 17 (5‐6), 553–586. Halgren, T. A.; Nachbar, R. B. Merck Molecular Force Field. IV. Conformational Energies and Geometries for MMFF94. J. Comput. Chem. 1996, 17 (5‐6), 587–615. Bannwarth, C.; Ehlert, S.; Grimme, S. GFN2-XTB—An Accurate and Broadly Parametrized Self-Consistent Tight-Binding Quantum Chemical Method with Multipole Electrostatics and Density-Dependent Dispersion Contributions. J. Chem. Theory Comput. 2019, 15 (3), 1652–1671. https://doi.org/10.1021/acs.jctc.8b01176. Stephens, P. J.; Devlin, F. J.; Chabalowski, C. F.; Frisch, M. J. Ab Initio Calculation of Vibrational Absorption and Circular Dichroism Spectra Using Density Functional Force Fields. J. Phys. Chem. 1994, 98 (45), 11623–11627. https://doi.org/10.1021/j100096a001. Becke, A. D. Density‐functional Thermochemistry. III. The Role of Exact Exchange. J. Chem. Phys. 1993, 98 (7), 5648–5652. https://doi.org/10.1063/1.464913. Chai, J.-D.; Head-Gordon, M. Long-Range Corrected Hybrid Density Functionals with Damped Atom–Atom Dispersion Corrections. Phys. Chem. Chem. Phys. 2008, 10 (44), 6615–6620. https://doi.org/10.1039/B810189B. Zhao, Y.; Truhlar, D. G. The M06 Suite of Density Functionals for Main Group Thermochemistry, Thermochemical Kinetics, Noncovalent Interactions, Excited States, and Transition Elements: Two New Functionals and Systematic Testing of Four M06-Class Functionals and 12 Other Functionals. Theor. Chem. Acc. 2008, 120 (1), 215–241. https://doi.org/10.1007/s00214-007-0310-x. Bakken, V.; Helgaker, T. The Efficient Optimization of Molecular Geometries Using Redundant Internal Coordinates. J. Chem. Phys. 2002, 117 (20), 9160–9174. https://doi.org/10.1063/1.1515483. Steinmetzer, J.; Kupfer, S.; Gräfe, S. Pysisyphus: Exploring Potential Energy Surfaces in Ground and Excited States. Int. J. Quantum Chem. 2021, 121 (3), e26390. https://doi.org/10.1002/qua.26390. Mnih, V.; Kavukcuoglu, K.; Silver, D.; Rusu, A. A.; Veness, J.; Bellemare, M. G.; Graves, A.; Riedmiller, M.; Fidjeland, A. K.; Ostrovski, G. Human-Level Control through Deep Reinforcement Learning. nature 2015, 518 (7540), 529–533. Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A. N.; Kaiser, Ł.; Polosukhin, I. Attention Is All You Need. Adv. Neural Inf. Process. Syst. 2017, 30, 5998–6008. Ba, J. L.; Kiros, J. R.; Hinton, G. E. Layer Normalization. ArXiv Prepr. ArXiv160706450 2016. Schütt, K. T.; Sauceda, H. E.; Kindermans, P.-J.; Tkatchenko, A.; Müller, K.-R. SchNet – A Deep Learning Architecture for Molecules and Materials. J. Chem. Phys. 2018, 148 (24), 241722. https://doi.org/10.1063/1.5019779. Rafati, J.; Marcia, R. F. Improving L-BFGS Initialization for Trust-Region Methods in Deep Learning. In 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA); 2018; pp 501–508. https://doi.org/10.1109/ICMLA.2018.00081. Hou, Z.; Zhang, K.; Wan, Y.; Li, D.; Fu, C.; Yu, H. Off-Policy Maximum Entropy Reinforcement Learning : Soft Actor-Critic with Advantage Weighted Mixture Policy(SAC-AWMP). arXiv February 7, 2020. http://arxiv.org/abs/2002.02829 (accessed 2022-11-16). Haarnoja, T.; Zhou, A.; Abbeel, P.; Levine, S. Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor. arXiv August 8, 2018. https://doi.org/10.48550/arXiv.1801.01290. Schulman, J.; Levine, S.; Moritz, P.; Jordan, M. I.; Abbeel, P. Trust Region Policy Optimization. arXiv April 20, 2017. https://doi.org/10.48550/arXiv.1502.05477. Schulman, J.; Wolski, F.; Dhariwal, P.; Radford, A.; Klimov, O. Proximal Policy Optimization Algorithms. ArXiv Prepr. ArXiv170706347 2017. Dadashi, R.; Hussenot, L.; Vincent, D.; Girgin, S.; Raichuk, A.; Geist, M.; Pietquin, O. Continuous Control with Action Quantization from Demonstrations. ArXiv211010149 Cs 2021. Ramakrishnan, R.; Dral, P. O.; Rupp, M.; von Lilienfeld, O. A. Quantum Chemistry Structures and Properties of 134 Kilo Molecules. Sci. Data 2014, 1 (1), 140022. https://doi.org/10.1038/sdata.2014.22. Wishart, D. S.; Feunang, Y. D.; Guo, A. C.; Lo, E. J.; Marcu, A.; Grant, J. R.; Sajed, T.; Johnson, D.; Li, C.; Sayeeda, Z.; Assempour, N.; Iynkkaran, I.; Liu, Y.; Maciejewski, A.; Gale, N.; Wilson, A.; Chin, L.; Cummings, R.; Le, D.; Pon, A.; Knox, C.; Wilson, M. DrugBank 5.0: A Major Update to the DrugBank Database for 2018. Nucleic Acids Res. 2018, 46 (Database issue), D1074–D1082. https://doi.org/10.1093/nar/gkx1037. Rdkit: The Official Sources for the RDKit Library. https:// github.com/rdkit/rdkit (accessed August 15, 2018). Nocedal, J. Updating Quasi-Newton Matrices with Limited Storage. Math. Comput. 1980, 35 (151), 773–782. Mishchenko, K. Regularized Newton Method with Global O(1/K^2) Convergence. arXiv April 27, 2022. https://doi.org/10.48550/arXiv.2112.02089. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/89490 | - |
| dc.description.abstract | 在計算化學領域中，分子的幾何構型優化是一項關鍵的步驟，而優化演算法的效率提升，對於縮減計算成本具有極其關鍵且不可或缺的影響力。在此研究中，我們引進了一種新穎的基於強化學習(reinforcement learning)的優化器(optimizer)，其效率超越了傳統的方法。我們的模型與眾不同之處在於其能夠將化學資訊整合至優化過程中。透過探索不同狀態表示法，像是結合梯度(gradient)、位移(displacements)、原始類型標籤(primitive type labels)，以及來自SchNet模型的額外化學資訊，我們的強化學習優化器展現了優異的成果。與傳統的優化演算法相比，特別是在處理較糟的初始幾何結構時，我們的方法所需的優化步數，平均減少了約50%。更重要的是，這種強化學習優化器在不同的理論層次上展現了可靠的通用性，突顯了其在提升分子幾何結構優化之領域的多樣性和潛力。這項研究強調了強化學習演算法可透過結合化學知識而提升效能的重要性，並為計算化學領域的未來開啟了新的可能性。 | zh_TW |
| dc.description.abstract | Geometry optimization is a crucial step in computational chemistry, and the efficiency of optimization algorithms plays a pivotal role in reducing computational costs. In this study, we introduce a novel reinforcement learning based optimizer that surpasses traditional methods in terms of efficiency. What sets our model apart is its ability to incorporate chemical information into the optimization process. By exploring different state representations that integrate gradients, displacements, primitive type labels, and additional chemical information from the SchNet model, our reinforcement learning optimizer achieves exceptional results. It demonstrates an average reduction of about 50% or more in optimization steps compared to the conventional optimization algorithms we examined, particularly when dealing with challenging initial geometries. Moreover, the reinforcement learning optimizer exhibits promising transferability across various levels of theory, emphasizing its versatility and potential for enhancing molecular geometry optimization. This research highlights the significance of leveraging reinforcement learning algorithms to harness chemical knowledge, paving the way for future advancements in the field of computational chemistry. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2023-09-07T17:14:03Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2023-09-07T17:14:03Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 序言 i
中文摘要 ii ABSTRACT iii CONTENTS iv LIST OF FIGURES vi LIST OF TABLES viii Chapter 1 Introduction 1 Chapter 2 Methods 5 2.1 Coordinates 5 2.1.1 Cartesian Coordinates 5 2.1.2 Internal Coordinates 5 2.1.3 Transforming Internal Coordinates into Cartesian Coordinates 5 2.2 Formulating RL for Geometry Optimization 6 2.3 Model Architecture of Policy Function 7 2.4 States, Actions, and Rewards 9 2.5 Training Model 13 2.6 Experimental Setup. 14 Chapter 3 Results and Discussion 17 3.1 Optimizer Benchmarks 17 3.2 Transferability Tests 23 3.3 Test Other Types of Action. 24 3.4 Analyzing Optimization Trajectories 27 Chapter 4 Conclusions 29 REFERENCE 30 APPENDICES 37 | - |
| dc.language.iso | en | - |
| dc.subject | 分子結構優化 | zh_TW |
| dc.subject | 強化學習 | zh_TW |
| dc.subject | 計算化學 | zh_TW |
| dc.subject | reinforcement learning | en |
| dc.subject | molecular geometry optimization | en |
| dc.subject | computational chemistry | en |
| dc.title | 化學資訊整合入強化學習以增強分子幾何結構優化 | zh_TW |
| dc.title | Integrating Chemical Information into Reinforcement Learning for Enhanced Molecular Geometry Optimization | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 111-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 林立強;林祥泰;簡思佳;林子仁 | zh_TW |
| dc.contributor.oralexamcommittee | Li-Chiang Lin;Shiang-Tai Lin;Szu-Chia Chien;Tzu-Jen Lin | en |
| dc.subject.keyword | 強化學習,分子結構優化,計算化學, | zh_TW |
| dc.subject.keyword | reinforcement learning,molecular geometry optimization,computational chemistry, | en |
| dc.relation.page | 40 | - |
| dc.identifier.doi | 10.6342/NTU202302321 | - |
| dc.rights.note | 同意授權(限校園內公開) | - |
| dc.date.accepted | 2023-08-04 | - |
| dc.contributor.author-college | 工學院 | - |
| dc.contributor.author-dept | 化學工程學系 | - |
| dc.date.embargo-lift | 2025-12-31 | - |
| 顯示於系所單位： | 化學工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-111-2.pdf 授權僅限NTU校內IP使用（校園外請利用VPN校外連線服務） | 1.74 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。