{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T20:37:45Z","timestamp":1770755865092,"version":"3.50.0"},"reference-count":60,"publisher":"ASME International","issue":"12","license":[{"start":{"date-parts":[[2024,11,5]],"date-time":"2024-11-05T00:00:00Z","timestamp":1730764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.asme.org\/publications-submissions\/publishing-information\/legal-policies"}],"content-domain":{"domain":["asmedigitalcollection.asme.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Bayesian optimization (BO) has become a powerful tool for solving simulation-based engineering optimization problems thanks to its ability to integrate physical and mathematical understandings, consider uncertainty, and address the exploitation\u2013exploration dilemma. Thompson sampling (TS) is a preferred solution for BO to handle the exploitation\u2013exploration tradeoff. While it prioritizes exploration by generating and minimizing random sample paths from probabilistic models\u2014a fundamental ingredient of BO\u2013TS weakly manages exploitation by gathering information about the true objective function after it obtains new observations. In this work, we improve the exploitation of TS by incorporating the \u03b5-greedy policy, a well-established selection strategy in reinforcement learning. We first delineate two extremes of TS, namely the generic TS and the sample-average TS. The former promotes exploration, while the latter favors exploitation. We then adopt the \u03b5-greedy policy to randomly switch between these two extremes. Small and large values of \u03b5 govern exploitation and exploration, respectively. By minimizing two benchmark functions and solving an inverse problem of a steel cantilever beam, we empirically show that \u03b5-greedy TS equipped with an appropriate \u03b5 is more robust than its two extremes, matching or outperforming the better of the generic TS and the sample-average TS.<\/jats:p>","DOI":"10.1115\/1.4066858","type":"journal-article","created":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T13:54:32Z","timestamp":1728914072000},"update-policy":"https:\/\/doi.org\/10.1115\/crossmarkpolicy-asme","source":"Crossref","is-referenced-by-count":9,"title":["Epsilon-Greedy Thompson Sampling to Bayesian Optimization"],"prefix":"10.1115","volume":"24","author":[{"given":"Bach","family":"Do","sequence":"first","affiliation":[{"name":"University of Houston Civil and Environmental Engineering, Uncertainty Quantification Laboratory, , Houston, TX 77204"}]},{"given":"Taiwo","family":"Adebiyi","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/048sx0r50","id-type":"ROR","asserted-by":"publisher"}],"name":"University of Houston Civil and Environmental Engineering, Uncertainty Quantification Laboratory, , Houston, TX 77204"},{"name":"University of Houston Civil and Environmental Engineering, Uncertainty Quantification Laboratory, , Houston, TX 77204"}]},{"given":"Ruda","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Houston Civil and Environmental Engineering, Uncertainty Quantification Laboratory, , Houston, TX 77204"}]}],"member":"33","published-online":{"date-parts":[[2024,11,5]]},"reference":[{"key":"2024110516140074900_CIT0001","first-page":"2951","article-title":"Practical Bayesian Optimization of Machine Learning Algorithms","author":"Snoek","year":"2012"},{"issue":"1","key":"2024110516140074900_CIT0002","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1109\/JPROC.2015.2494218","article-title":"Taking the Human out of the Loop: A Review of Bayesian Optimization","volume":"104","author":"Shahriari","year":"2016","journal-title":"Proc. IEEE"},{"key":"2024110516140074900_CIT0003","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1287\/educ.2018.0188","article-title":"Bayesian Optimization","volume-title":"Recent Advances in Optimization and Modeling of Contemporary Problems","author":"Frazier","year":"2018"},{"key":"2024110516140074900_CIT0004","doi-asserted-by":"crossref","DOI":"10.1017\/9781108348973","volume-title":"Bayesian Optimization","author":"Garnett","year":"2023"},{"key":"2024110516140074900_CIT0005","author":"Do","year":"2023"},{"issue":"4","key":"2024110516140074900_CIT0006","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1615\/JMachLearnModelComput.2024055786","article-title":"Multi-fidelity Machine Learning for Uncertainty Quantification and Optimization","volume":"5","author":"Zhang","year":"2024","journal-title":"J. Machine Learn. Model. Comput."},{"key":"2024110516140074900_CIT0007","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.mfglet.2022.02.001","article-title":"Bayesian Optimization for Inverse Calibration of Expensive Computer Models: A Case Study for Johnson-Cook Model in Machining","volume":"32","author":"Karandikar","year":"2022","journal-title":"Manuf. Lett."},{"issue":"3","key":"2024110516140074900_CIT0008","doi-asserted-by":"publisher","first-page":"1489","DOI":"10.1007\/s11081-021-09663-7","article-title":"Identifying Material Parameters in Crystal Plasticity by Bayesian Optimization","volume":"23","author":"Kuhn","year":"2022","journal-title":"Optim. Eng."},{"issue":"6","key":"2024110516140074900_CIT0009","doi-asserted-by":"publisher","first-page":"2131","DOI":"10.1007\/s00158-018-2182-1","article-title":"Constrained Mixed-Integer Gaussian Mixture Bayesian Optimization and Its Applications in Designing Fractal and Auxetic Metamaterials","volume":"59","author":"Tran","year":"2019","journal-title":"Struct. Multidiscipl. Optim."},{"issue":"1","key":"2024110516140074900_CIT0010","doi-asserted-by":"publisher","first-page":"4924","DOI":"10.1038\/s41598-020-60652-9","article-title":"Bayesian Optimization for Materials Design With Mixed Quantitative and Qualitative Variables","volume":"10","author":"Zhang","year":"2020","journal-title":"Sci. Rep."},{"issue":"1","key":"2024110516140074900_CIT0011","doi-asserted-by":"publisher","first-page":"013107","DOI":"10.1103\/PhysRevE.101.013107","article-title":"Multifidelity Kinematic Parameter Optimization of a Flapping Airfoil","volume":"101","author":"Zheng","year":"2020","journal-title":"Phys. Rev. E"},{"key":"2024110516140074900_CIT0012","doi-asserted-by":"publisher","first-page":"13937","DOI":"10.1109\/ACCESS.2020.2966228","article-title":"Bayesian Optimization for Adaptive Experimental Design: A Review","volume":"8","author":"Greenhill","year":"2020","journal-title":"IEEE Access"},{"issue":"6","key":"2024110516140074900_CIT0013","doi-asserted-by":"publisher","first-page":"062801","DOI":"10.1103\/PhysRevAccelBeams.24.062801","article-title":"Multiobjective Bayesian Optimization for Online Accelerator Tuning","volume":"24","author":"Roussel","year":"2021","journal-title":"Phys. Rev. Accel. Beams"},{"key":"2024110516140074900_CIT0014","doi-asserted-by":"crossref","DOI":"10.1017\/9781316681411","volume-title":"Probabilistic Numerics: Computation as Machine Learning","author":"Hennig","year":"2022"},{"issue":"4","key":"2024110516140074900_CIT0015","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1007\/s10898-008-9354-2","article-title":"An Informational Approach to the Global Optimization of Expensive-to-Evaluate Functions","volume":"44","author":"Villemonteix","year":"2009","journal-title":"J. Global Optim."},{"issue":"6","key":"2024110516140074900_CIT0016","first-page":"1809","article-title":"Entropy Search for Information-Efficient Global Optimization","volume":"13","author":"Hennig","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"2024110516140074900_CIT0017","first-page":"918","article-title":"Predictive Entropy Search for Efficient Global Optimization of Black-Box Functions","author":"Hern\u00e1ndez-Lobato","year":"2014"},{"key":"2024110516140074900_CIT0018","first-page":"3627","article-title":"Max-Value Entropy Search for Efficient Bayesian Optimization","author":"Wang","year":"2017"},{"issue":"4","key":"2024110516140074900_CIT0019","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1023\/A:1008306431147","article-title":"Efficient Global Optimization of Expensive Black-Box Functions","volume":"13","author":"Jones","year":"1998","journal-title":"J. Global Optim."},{"issue":"1","key":"2024110516140074900_CIT0020","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/s10898-004-6733-1","article-title":"On the Design of Optimization Strategies Based on Global Response Surface Approximation Models","volume":"33","author":"S\u00f3bester","year":"2005","journal-title":"J. Global Optim."},{"key":"2024110516140074900_CIT0021","first-page":"1015","article-title":"Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design","author":"Srinivas","year":"2010"},{"issue":"5","key":"2024110516140074900_CIT0022","doi-asserted-by":"publisher","first-page":"2410","DOI":"10.1137\/070693424","article-title":"A Knowledge-Gradient Policy for Sequential Information Collection","volume":"47","author":"Frazier","year":"2008","journal-title":"SIAM J. Control Optim."},{"key":"2024110516140074900_CIT0023","doi-asserted-by":"publisher","first-page":"109901","DOI":"10.1016\/j.jcp.2020.109901","article-title":"Bayesian Optimization With Output-Weighted Optimal Sampling","volume":"425","author":"Blanchard","year":"2021","journal-title":"J. Comput. Phys."},{"issue":"3\/4","key":"2024110516140074900_CIT0024","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1093\/biomet\/25.3-4.285","article-title":"On the Likelihood That One Unknown Probability Exceeds Another in View of the Evidence of Two Samples","volume":"25","author":"Thompson","year":"1933","journal-title":"Biometrika"},{"key":"2024110516140074900_CIT0025","first-page":"2249","article-title":"An Empirical Evaluation of Thompson Sampling","author":"Chapelle","year":"2011"},{"issue":"4","key":"2024110516140074900_CIT0026","doi-asserted-by":"publisher","first-page":"1221","DOI":"10.1287\/moor.2014.0650","article-title":"Learning to Optimize Via Posterior Sampling","volume":"39","author":"Russo","year":"2014","journal-title":"Math. Oper. Res."},{"issue":"1","key":"2024110516140074900_CIT0027","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2200000070","article-title":"A Tutorial on Thompson Sampling","volume":"11","author":"Russo","year":"2018","journal-title":"Found. Trends\u00ae Mach. Learn."},{"key":"2024110516140074900_CIT0028","first-page":"133","article-title":"Parallelised Bayesian Optimisation Via Thompson Sampling","author":"Kandasamy","year":"2018"},{"key":"2024110516140074900_CIT0029","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"issue":"1","key":"2024110516140074900_CIT0030","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3425501","article-title":"Greed is Good: Exploration and Exploitation Trade-Offs in Bayesian Optimisation","volume":"1","author":"De Ath","year":"2021","journal-title":"ACM Trans. Evolutionary Learn. Optim."},{"key":"2024110516140074900_CIT0031","first-page":"15239","article-title":"Thompson Sampling With Less Exploration is Fast and Optimal","author":"Jin","year":"2023"},{"key":"2024110516140074900_CIT0032","volume-title":"Gaussian Processes for Machine Learning","author":"Rasmussen","year":"2006"},{"key":"2024110516140074900_CIT0033","volume-title":"Pattern Recognition and Machine Learning","author":"Bishop","year":"2006"},{"key":"2024110516140074900_CIT0034","volume-title":"Information Theory, Inference and Learning Algorithms","author":"MacKay","year":"2003"},{"key":"2024110516140074900_CIT0035","author":"Lophaven","year":"2002"},{"issue":"100","key":"2024110516140074900_CIT0036","first-page":"3011","article-title":"Gaussian Processes for Machine Learning (GPML) Toolbox","volume":"11","author":"Rasmussen","year":"2010","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"2024110516140074900_CIT0037","first-page":"1175","article-title":"GPstuff: Bayesian Modeling With Gaussian Processes","volume":"14","author":"Vanhatalo","year":"2013","journal-title":"J. Mach. Learn. Res."},{"issue":"80","key":"2024110516140074900_CIT0038","first-page":"2611","article-title":"pyGPs \u2013 A Python Library for Gaussian Process Regression and Classification","volume":"16","author":"Neumann","year":"2015","journal-title":"J. Mach. Learn. Res."},{"issue":"40","key":"2024110516140074900_CIT0039","first-page":"1","article-title":"GPflow: A Gaussian Process Library Using TensorFlow","volume":"18","author":"de G. Matthews","year":"2017","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"2024110516140074900_CIT0040","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/s11222-022-10167-2","article-title":"Practical Hilbert Space Approximate Bayesian Gaussian Processes for Probabilistic Programming","volume":"33","author":"Riutort-Mayol","year":"2022","journal-title":"Stat. Comput."},{"key":"2024110516140074900_CIT0041","first-page":"1177","article-title":"Random Features for Large-Scale Kernel Machines","author":"Rahimi","year":"2007"},{"key":"2024110516140074900_CIT0042","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511617539","volume-title":"Scattered Data Approximation","author":"Wendland","year":"2004"},{"key":"2024110516140074900_CIT0043","first-page":"10292","article-title":"Efficiently Sampling Functions From Gaussian Process Posteriors","author":"Wilson","year":"2020"},{"key":"2024110516140074900_CIT0044","first-page":"21524","article-title":"BoTorch: A Framework for Efficient Monte-Carlo Bayesian Optimization","author":"Balandat","year":"2020"},{"key":"2024110516140074900_CIT0045","author":"Adebiyi","year":"2024"},{"issue":"7","key":"2024110516140074900_CIT0046","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1007\/s00158-022-03297-8","article-title":"Proximal-Exploration Multi-objective Bayesian Optimization for Inverse Identification of Cyclic Constitutive Law of Structural Steels","volume":"65","author":"Do","year":"2022","journal-title":"Struct. Multidiscipl. Optim."},{"key":"2024110516140074900_CIT0047","author":"Surjanovic","year":"2013"},{"issue":"4","key":"2024110516140074900_CIT0048","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1007\/s10898-006-9029-9","article-title":"Additive Scaling and the DIRECT Algorithm","volume":"36","author":"Finkel","year":"2006","journal-title":"J. Global Optim."},{"key":"2024110516140074900_CIT0049","doi-asserted-by":"crossref","DOI":"10.1002\/9780470770801","volume-title":"Engineering Design Via Surrogate Modelling: A Practical Guide","author":"Forrester","year":"2008"},{"issue":"3","key":"2024110516140074900_CIT0050","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1007\/s13296-015-0134-9","article-title":"A Concise Hysteretic Model of Structural Steel Considering the Bauschinger Effect","volume":"16","author":"Yamada","year":"2016","journal-title":"Int. J. Steel Struct."},{"issue":"4","key":"2024110516140074900_CIT0051","doi-asserted-by":"publisher","first-page":"303","DOI":"10.3970\/cmes.2016.111.303","article-title":"A Piecewise Linear Isotropic-Kinematic Hardening Model With Semi-Implicit Rules for Cyclic Loading and Its Parameter Identification","volume":"111","author":"Ohsaki","year":"2016","journal-title":"Comput. Model. Eng. Sci."},{"key":"2024110516140074900_CIT0052","volume-title":"Mechanics of Solid Materials","author":"Lemaitre","year":"1994"},{"key":"2024110516140074900_CIT0053","first-page":"537","article-title":"The Relationship Between Stress and Strain for Homogeneous Deformation","volume":"74","author":"Voce","year":"1948","journal-title":"J. Inst. Metals"},{"issue":"2","key":"2024110516140074900_CIT0054","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1115\/1.3264257","article-title":"On the Plastic and Viscoplastic Constitutive Equations\u2013Part I: Rules Developed With Internal Variable Concept","volume":"105","author":"Chaboche","year":"1983","journal-title":"ASME J. Pressure Vessel. Technol."},{"key":"2024110516140074900_CIT0055","author":"Armstrong","year":"1966"},{"key":"2024110516140074900_CIT0056","first-page":"4752","article-title":"A Framework for Bayesian Optimization in Embedded Subspaces","author":"Nayebi","year":"2019"},{"issue":"3","key":"2024110516140074900_CIT0057","doi-asserted-by":"publisher","first-page":"A1428","DOI":"10.1137\/21M1432739","article-title":"Gaussian Process Subspace Prediction for Model Reduction","volume":"44","author":"Zhang","year":"2022","journal-title":"SIAM J. Sci. Comput."},{"key":"2024110516140074900_CIT0058","first-page":"5496","article-title":"Scalable Global Optimization Via Local Bayesian Optimization","author":"Eriksson","year":"2019"},{"key":"2024110516140074900_CIT0059","first-page":"6797","article-title":"On Approximate Thompson Sampling With Langevin Algorithms","author":"Mazumdar","year":"2020"},{"key":"2024110516140074900_CIT0060","first-page":"2611","article-title":"Accelerating Approximate Thompson Sampling With Underdamped Langevin Monte Carlo","author":"Zheng","year":"2024"}],"container-title":["Journal of Computing and Information Science in Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/24\/12\/121006\/7400362\/jcise_24_12_121006.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/24\/12\/121006\/7400362\/jcise_24_12_121006.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,5]],"date-time":"2024-11-05T16:14:16Z","timestamp":1730823256000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article\/24\/12\/121006\/1207209\/Epsilon-Greedy-Thompson-Sampling-to-Bayesian"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,5]]},"references-count":60,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2024,12,1]]}},"URL":"https:\/\/doi.org\/10.1115\/1.4066858","relation":{},"ISSN":["1530-9827","1944-7078"],"issn-type":[{"value":"1530-9827","type":"print"},{"value":"1944-7078","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,5]]},"article-number":"121006"}}